Music

Stream music with details: Added Stream music with details (POST /v1/music/detailed/stream) for SSE streaming of composed audio plus detailed metadata, including composition plan, song metadata, base64 audio chunks and optional word timestamps via with_timestamps.

ElevenAgents

Simulate conversation deprecation: Simulate conversation and Stream simulate conversation are deprecated in favor of Create test and Run tests on the agent.

Tool interruption mode: disable_interruptions is deprecated across agent tool and MCP server schemas. Use interruption_mode (ToolInterruptionMode: allow, disable_during_tool, disable_during_tool_and_turn) instead, with per-tool overrides via interruption_mode on tool override models.

Numeric evaluation scoring: Evaluation criteria schemas add optional scoring_mode (binary | numeric_uniform), optional max_score (integer) and optional score_instructions (string). Evaluation results add optional numeric score. Conversation analysis payloads add optional call_success_score and success_score.

Conversation reasoning: Transcript and history models add optional reasoning (ConversationReasoningModel) and transcript responses add optional reasoned (boolean). Agent prompt and LLM schemas add optional enable_reasoning_summary (boolean).

Conversation platform billing: Conversation-related models add optional platform_charge, platform_price and platform_usage with per-category breakdown via PlatformCategory and PlatformCategoryUsage.

Conversation cost metadata: Conversation history metadata adds required read-only cost_fiat (number, USD).

Unredacted webhook events: WebhookEventType adds unredacted_transcript and unredacted_audio for webhook subscriptions that need unredacted payloads.

Workflow phone transfer UUI limit: UUITransferConfig.data maximum length increases from 256 to 8192 characters for RFC 7433 User-to-User Information on SIP REFER transfers.

Speech Engine

Optional authentication bypass: JavaScript and Python SDK v2.56.0 add optional disableAuth / disable_auth on Speech Engine WebSocket clients. This is intended for integrations that protect the connection through other means, such as IP allowlisting or custom authentication headers, rather than API key authentication.

Workspaces

Professional voice slot tracking: Subscription-style models add optional professional_voice_slots_used_in_workspace alongside clarified group-wide professional_voice_slots_used for consolidated billing visibility.

ElevenCreative Studio

Caption styling: Caption style models add blur and border-radius fields. Enter and exit animation enums add slam, scale_down and slide_in.

SDK Releases

JavaScript SDK

v2.56.0 - Added optional disableAuth on Speech Engine WebSocket clients. Regenerated from the latest OpenAPI schema with music detailed streaming, tool interruption_mode, evaluation scoring modes, conversation reasoning and platform billing fields.

Python SDK

v2.56.0 - Added optional disable_auth on Speech Engine WebSocket clients. Regenerated from the latest OpenAPI schema with music detailed streaming, tool interruption_mode, evaluation scoring modes, conversation reasoning and platform billing fields.

CLI

@elevenlabs/[email protected] - Agent create and update requests are now sent as raw JSON to preserve configuration round-trip fidelity.

API

Original source

ElevenAgents

Branch merge and rebase previews: Added Preview merged configuration (GET /v1/convai/agents/{agent_id}/branches/{source_branch_id}/merge-preview) and preview rebased configuration (GET /v1/convai/agents/{agent_id}/branches/{branch_id}/rebase-preview) to inspect merged or rebased agent configuration before committing. Both return MergePreviewResponseModel with the resulting config, overridden_fields, and source_identical_to_target.

Branch usage metrics: List agent branches branch summary responses add optional calls_7d (integer) with seven-day call volume per branch.

Auth connection status: Workspace auth connection response models replace OAuth-only OAuthConnectionStatus with shared AuthConnectionStatus (active, refresh_failed, revoked, credential_invalid). Bearer, Basic, mTLS, custom header, OAuth, OAuth2 JWT, Slack, URL secret and WhatsApp auth responses add optional status, status_detail and status_updated_at fields.

Tool response filtering: HTTP and agent tool configuration schemas add optional response_filter to trim tool responses before they reach the LLM, with response_filter_mode and response_filters on related override models.

Workflow phone transfers: Workflow phone-number transfer nodes add optional require_acceptance (boolean, default false) and optional uui (UUITransferConfig) for RFC 7433 hex User-to-User Information on SIP REFER transfers.

Telephony agent assignment: Twilio, Exotel and SIP trunk phone-number import request schemas add optional agent_id (string) to assign an agent during number setup.

Turn transcription on disabled interruptions: Turn configuration schemas add optional transcribe_on_disabled_interruptions (boolean, default false) to control whether user speech is transcribed when interruptions are disabled.

Conversation sentiment: Conversation summary schemas add optional sentiment_analysis. Conversation user models add optional sentiment with frustrated-conversation references.

Speech to Text

Combined multichannel output: Convert speech to text adds optional multichannel_output_style (separate default | combined) when use_multi_channel is enabled. Set combined to receive a single transcript with all channels merged and sorted by time instead of per-channel transcripts. Word-level responses include channel_index on each word when multichannel mode is active.

Text to Speech

language_code behavior: TTS request schemas clarify that unsupported language_code values are ignored rather than rejected, and that language_code is not supported on multilingual_v2 models.

Workspaces

Third-party API key disabling policy: Added Set workspace third-party disabling policy (POST /v1/workspaces/api-keys/third-party-disabling) for workspace-wide control over whether API key holders can self-disable keys via the third-party disable endpoint. Workspace API key create, patch and response models add optional third_party_disable_allowed (boolean).

Bearer auth connection updates: Update workspace auth connection request union adds UpdateBearerAuthRequest for bearer token credential updates.

Workspace permissions: Permission enums add conversation_privacy_manage and synthid_detector. Workspace group models add optional scim_group (string).

SDK Releases

JavaScript SDK

v2.55.0 - Regenerated from the latest OpenAPI schema with branch merge and rebase preview clients, branch call-volume metrics, auth connection status fields, tool response filtering types, speech-to-text combined multichannel output, and workspace third-party API key disabling policy.

Python SDK

v2.55.0 - Regenerated from the latest OpenAPI schema with branch merge and rebase preview clients, branch call-volume metrics, auth connection status fields, tool response filtering models, speech-to-text combined multichannel output, and workspace third-party API key disabling policy.

Packages

@elevenlabs/[email protected] - sendFeedback(like, eventId?) accepts an optional event_id to rate a specific past message. canSendFeedback now reflects connection state so feedback can be sent for any message while the session is live.

@elevenlabs/[email protected] - sendFeedback accepts null as the first argument to clear feedback on an event (score: null).

@elevenlabs/[email protected] and @elevenlabs/[email protected] - Exposed the per-message and clear-feedback sendFeedback changes from @elevenlabs/[email protected] and @elevenlabs/[email protected] in React hooks.

@elevenlabs/[email protected] and @elevenlabs/[email protected] - Dependency alignment to @elevenlabs/[email protected]–1.14.0 and @elevenlabs/[email protected]–1.9.0.

@elevenlabs/[email protected], @elevenlabs/[email protected]–0.14.8 and @elevenlabs/[email protected]–0.14.8 - Dependency alignment to @elevenlabs/[email protected]–1.14.0.

Android SDK

v0.10.0 - Exposed reconciled message transcript as StateFlow. Deprecated text and agent callbacks in favor of event-id variants.

v0.11.0 - Added audio frame callback for per-frame audio inspection during conversations.

iOS SDK

v3.2.2 - Fixed LiveKit room delegate method implementation for correct room event handling.

API

Original source

ElevenAgents

Branch rebase: Added POST /v1/convai/agents/{agent_id}/branches/{branch_id}/rebase to rebase a branch onto the latest main while preserving branch-specific changes. Agent version parent models add optional rebased_from_version_id (string) to track the source version after a rebase.

Conversation product filtering: List conversations and Text search conversation messages add optional conversation_product_type query parameter (agents | speech_engine) to filter results by product. Conversation models introduce ConversationProduct for this distinction.

Conversation termination filtering: List conversations adds optional termination_reasons query parameter (array of strings) to filter conversations by how they ended.

Per-agent topic discovery: Create agent and Update agent platform settings add optional topic_discovery (TopicDiscoverySettings) for per-agent topic discovery configuration.

Background sound configuration: Agent platform and conversation configuration models add optional background_sound (BackgroundSoundConfig) for ambient audio during conversations.

Turn interruption ignore terms: Turn configuration schemas add optional interruption_ignore_terms (array of strings) to suppress turn detection on specific phrases.

Soft timeout filler randomization: Soft timeout configuration adds optional randomize_fillers (boolean) to shuffle filler messages across soft timeouts. Soft timeout message and LLM prompt override fields now support dynamic variables.

Transcript user identifiers: Transcript message models add optional user_identifier (string) on user-authored messages.

Simulation success conditions: Agent simulation test schemas add optional success_conditions (array, up to 30 items). The legacy success_condition field is deprecated in favor of the array form.

Agent test repeat limit: Run tests on the agent raises the maximum repeat_count from 20 to 50.

Tool schema dynamic allowed values: ElevenAgents tool JSON schema properties add optional allowed_values_dynamic_variable (string) for server-verified LLM value picks sourced from dynamic variables.

Widget signed URL docs: Get widget updates conversation_signature documentation to reference /v1/convai/conversation/get_signed_url.

Music

Higher-quality output formats: Generate music, Generate music detailed and Stream music add mp3_48000_240 and mp3_48000_320 to supported output_format values. When output_format is auto, v2 models now default to mp3_48000_192 instead of mp3_48000_128.

Section duration flag clarification: respect_sections_durations applies only with composition_plan on music_v1. On music_v2, section durations are always enforced and this flag is ignored.

Composition plan schema split: Music request composition_plan uses a oneOf union of MusicPrompt and CompositionPlan. The former is used for music_v1 composition plans and the latter for music_v2.

Dubbing

Project list filters: List dubs adds optional dubbing_statuses, dubbing_models, target_language_codes and creation_sources array query parameters for filtered listing. The order_by parameter now accepts name in addition to created_at.

Workspaces

Lock and disable reasons: Workspace and API key models add LockReason and optional disable_reason fields. Workspace group settings add optional scim_frozen (boolean) for SCIM-managed freeze state.

ElevenCreative Studio

Caption animations: Studio caption enter and exit animation enums add pop, slide_up and slide_down.

SDK Releases

JavaScript SDK

v2.54.0 - Regenerated from the latest OpenAPI schema with branch rebase client support, conversation list and text-search conversation_product_type and termination_reasons filters, dubbing list multi-value filters, music-specific output_format types, topic discovery settings, and removal of coaching-related exported types.

v2.53.1 - Restored optional values in DynamicVariablesConfig records that were incorrectly narrowed in v2.53.0.

Python SDK

v2.54.0 - Regenerated from the latest OpenAPI schema with branch rebase client support, conversation list and text-search filters, dubbing list multi-value filters, music output format updates, topic discovery settings, and removal of coaching-related exported types. ElevenLabs and AsyncElevenLabs now accept headers and follow_redirects passthrough to the base client.

Packages

@elevenlabs/[email protected] - Added overrides.asr.keywords support on the browser client so per-conversation ASR keyword biasing can be sent via conversation_initiation_client_data.

@elevenlabs/[email protected] - Exposed includeLanguageDetection for realtime Scribe sessions, including React useScribe support for requesting and reading detected language metadata.

@elevenlabs/[email protected], @elevenlabs/[email protected], @elevenlabs/[email protected] and @elevenlabs/[email protected] - Dependency alignment to @elevenlabs/[email protected] and @elevenlabs/[email protected].

@elevenlabs/[email protected] - Exposed the file upload helper from the internal Unity entrypoint.

@elevenlabs/[email protected], @elevenlabs/[email protected], @elevenlabs/[email protected] and @elevenlabs/[email protected] - Dependency alignment to @elevenlabs/[email protected].

MCP Server

v0.10.0 - Added Music v2 model and endpoints, MCP tool annotations for all 24 tools, Python 3.14 support, Singapore data residency, EU/IN residency shorthand aliases, graceful shutdown handling for client disconnections, and fixes for voice preview creation and output directory path resolution.

API

Original source

Introducing Music v2

Music v2 is now available via the ElevenLabs API. Set model_id to music_v2 on Generate music, Stream music, Generate music detailed and Upload music to use the new model. Music v2 introduces chunk-based composition plans built from GenerationChunk and AudioRefChunk segments, giving you finer control over structure, pacing and arrangement than the prompt-based music_v1 flow.

Use music_v2 composition plans on generation and upload requests, or generate a plan first via the composition-plan endpoint. Request and response bodies accept either v1 or v2 plan shapes, so you can migrate endpoint by endpoint. MusicPrompt remains available for music_v1 only.

Upload timestamps: Upload music accepts optional with_timestamps; responses may include words_timestamps.

ElevenAgents

Run conversation evaluation: Added Run conversation evaluation endpoint (POST /v1/convai/conversations/{conversation_id}/analysis/evaluations/run) to rerun a single evaluation criterion against a completed conversation using RunConversationEvaluationsRequest.

Workflow entry behavior: Workflow override-agent nodes add optional entry_behavior (generate_immediately, wait_for_user, auto) to control whether the sub-agent speaks first or waits for user input.

End procedure system tool: Added end_procedure system tool configuration with matching error statuses. The start_procedure tool adds already_active to its error statuses.

Transfer TTS overrides: AgentTransfer, workflow standalone agent nodes and successful transfer_to_agent tool results add optional preserve_client_tts_overrides (boolean) to keep client-side TTS overrides after a transfer.

Interaction budget enum: InteractionBudget removes async and adds 5_minutes, 10_minutes and 1_hour. Update any configs or SDK enums that still reference async.

Custom guardrail model selection: Custom guardrail configuration adds optional model with Gemini, Claude and GPT variants. Guardrail config also adds optional history_message_count (integer).

Phone number list filters: List phone numbers adds optional provider, agent_id and branch_id query parameters to filter imported numbers.

WhatsApp account filtering: List WhatsApp accounts adds optional agent_id query parameter to filter accounts by assigned agent.

Topic time range filters: Get agent conversation topics adds optional from_unix_secs and to_unix_secs query parameters to bound topic discovery results.

SIP codec configuration: Outbound SIP trunk request and response models add optional enabled_codecs (MediaCodec enum).

Memory tool types: Added LoadableMemoryEntry and LoadMemoryEntryToolErrorStatus schemas for memory-tool error handling.

Agent test batch limits: Agent test attach, run and resubmit request schemas raise maximum attached tests from 1000 to 5000.

Phoneme tag support: Agent TTS settings add optional enable_phoneme_tags (boolean) for opt-in V3 SSML phoneme handling.

Array schema omit overrides: Array JSON schema properties add optional is_omitted (mutually exclusive with other value sources). ConstantSchemaOverride can use array constant values.

Transfer error context: Transfer-to-number error payloads can include optional agent_message (string).

Workspaces

Service account API key updates: Update service account API key no longer requires a request body. Edit fields support partial updates via no_update and nullable name, including permissions and character_limit.

Usage timezone bucketing: Workspace usage-by-product-over-time requests add optional time_zone (IANA timezone string) with clarified interval_seconds bucket rules.

History source filter: History list and detail source filters add Flows.

ElevenCreative Studio

Project voice references: Project models, chapter TTS nodes, voice lists and voice statistics shift to project_voice_ref_id as the canonical voice field. Former voice_id fields remain on responses as deprecated, read-only mirrors for compatibility.

Speech to Text

Speaker library diarization: Convert speech to text adds optional use_speaker_library (boolean, default false) for batch transcription diarization.

Voices

Shared voice sorting: List shared voicessort query parameter gains an explicit enum, created_date default and updated description.

SDK Releases

JavaScript SDK

v2.53.0 - Regenerated from the latest OpenAPI schema with conversation evaluation rerun support, music v2 composition-plan unions, workflow entry_behavior, phone number and WhatsApp list filters, topic time-range parameters, alerting schema updates, studio project_voice_ref_id fields, and expanded agent test batch limits.

Python SDK

v2.53.0 - Regenerated from the latest OpenAPI schema with conversation evaluation rerun support, music v2 composition plans, workflow entry behavior and end-procedure tools, telephony filter parameters, alerting and service-account partial-update models, and studio voice reference fields.

Packages

@elevenlabs/[email protected] - Added @elevenlabs/client/internal/unity sub-path export for the Unity SDK WebGL bridge, exposing MediaDeviceInput, MediaDeviceOutput, connection attach helpers and WebRTC adapter types.

@elevenlabs/[email protected], @elevenlabs/[email protected], @elevenlabs/[email protected], @elevenlabs/[email protected] and @elevenlabs/[email protected] - Dependency alignment to @elevenlabs/[email protected] and @elevenlabs/[email protected].

@elevenlabs/[email protected] - Added "license": "MIT" to package.json for license-checker compatibility.

iOS SDK

v3.2.1 - Added Singapore data residency support and enabled singlePeerConnection for WebRTC sessions.

API

Original source

Text to Speech

v1 model removal: The eleven_monolingual_v1 and eleven_multilingual_v1 models are deprecated and will be removed on July 9, 2026. Migrate to eleven_multilingual_v2 or another current model before removal. See deprecated models for replacement suggestions.

Speech to Text

Scribe v1 removal: The scribe_v1 model is deprecated and will be removed on July 9, 2026. Migrate to scribe_v2 or scribe_v2_realtime before removal. See deprecated models for replacement suggestions.

ElevenAgents

Turn model configuration: TurnConfig and TurnConfigWorkflowOverride add optional turn_model (turn_v2 or turn_v3, default turn_v3) to select the turn detection model version per agent or workflow node.

Soft timeout filler messages: SoftTimeoutConfig and SoftTimeoutConfigWorkflowOverride add optional additional_soft_timeout_messages (array of strings, up to 7) and max_soft_timeouts_per_generation (integer, 1–8, default 1). The primary message applies to the first timeout; subsequent timeouts use the additional messages or a built-in filler.

ASR provider default: The default ASRConversationalConfig.provider value changes from elevenlabs to scribe_realtime. The elevenlabs value remains in the enum but is deprecated.

Conversation product field: Get conversation details response adds optional conversation_product (string, default agent) to identify the product that handled the conversation.

Knowledge base external sync: Knowledge base file and folder response models add optional external_sync_info (Google Drive sync metadata via ExternalFileSyncInfo / ExternalFolderSyncInfo) and optional is_frozen (boolean) to indicate whether synced content can be edited.

Tool schema omit overrides: ConvAI tool JSON schema properties add optional is_omitted (boolean) and OmitSchemaOverride with source: omit, allowing fields to be explicitly omitted from tool payloads.

Procedure guardrails: Procedure version schemas add optional guardrails.

Workspaces

URL secret auth connections: Workspace auth connection create, list and response unions add url_secret (UrlSecretAuthResponse) as a supported auth connection type for tools that fetch secrets from a URL.

Agent QA Evaluations webhooks: WebhookUsageType adds Agent QA Evaluations as a webhook usage category for agent quality-assurance event delivery.

Text to Dialogue

Zero retention mode: Convert text to dialogue, Stream text to dialogue, Convert text to dialogue with timestamps and Stream text to dialogue with timestamps add optional enable_logging query parameter (boolean, default true). Set enable_logging=false to use zero retention mode with no history or request stitching. Zero retention mode is available to enterprise customers only.

ElevenCreative Studio

Safesearch adult metadata: Get projectpublishing_read responses add optional safesearch_adult (nullable boolean) on DirectPublishingReadResponseModel for direct publishing content classification.

SDK Releases

JavaScript SDK

v2.52.0 - Regenerated from the latest OpenAPI schema with turn_model and soft timeout filler fields on turn configs, knowledge base external sync types, OmitSchemaOverride for tool schemas, UrlSecretAuthResponse, conversation_product on conversation responses, text-to-dialogue enable_logging support, and updated AsrProvider defaults.

v2.51.0 - Added workspace API key revoke client, ConversationSentimentAnalysis and SystemEvaluationCriteria types, CustomLlmAuthConnection for HTTP tool auth, procedure tool config types, ResourceAccessInfoAccessSource, and conversation list/search filters for workflow_node_entered_id and topic_ids.

Python SDK

v2.52.0 - Regenerated from the latest OpenAPI schema with turn model and soft timeout config updates, knowledge base external sync models, tool schema omit overrides, URL secret auth connections, conversation conversation_product, text-to-dialogue enable_logging support, and updated ASR provider defaults.

v2.51.0 - Regenerated from the latest OpenAPI schema with workspace API key revoke, conversation sentiment and system evaluation types, procedure tool configuration models, and updated conversation filtering parameters.

Packages

@elevenlabs/[email protected] and @elevenlabs/[email protected] - Added call and message entry points to the widget launcher. Multimodal agents show both; voice-only agents show call; text-only agents show message.

@elevenlabs/[email protected] and @elevenlabs/[email protected] - Fixed compact and full trigger control alignment.

API

Original source

ElevenAgents

Exotel telephony integration: Added Exotel as a first-class telephony provider alongside Twilio and SIP trunking. New Exotel outbound call endpoint (POST /v1/convai/exotel/outbound-call) initiates outbound calls via the Exotel Connect API with agent_id, agent_phone_number_id, to_number, optional conversation_initiation_client_data and optional telephony_call_config. Exotel phone number create, list, get and update schemas are available, and exotel is added to TelephonyProvider, conversation initiation source and transfer result enums.

Workflow-aware agent transfers: AgentTransfer now allows a nullable agent_id so transfers can stay on the current agent, adds optional node_id to start at a specific node in the destination workflow, and only requires condition. Successful transfer_to_agent tool results can include nullable to_node, aligning transfers with workflow-node targets.

Agent test repeat runs: Run tests on the agent accepts optional repeat_count (integer, 1–20, default 1) to run each test multiple times. When repeat_count is greater than 1, responses include bucketing_status and result_groups for grouped summaries. Unit test create, update and summary schemas add optional conversation_initiation_source so tests can simulate a specific channel.

Conversation filtering: List conversations adds optional workflow_node_entered_id (string) to filter conversations that entered a given workflow node. Text search conversation messages adds optional topic_ids (array of strings) to filter by topic IDs assigned during topic discovery.

Agent versioning query parameters deprecated: enable_versioning on create agent and enable_versioning_if_not_enabled on update agent are marked deprecated. All agents are versioned and these parameters are ignored.

Procedure compiler mode: Removed append from ProcedureCompilerMode.

Workspaces

Revoke API key: Added revoke API key endpoint (DELETE /v1/workspaces/api-keys/revoke) with required api_key_name query parameter to revoke a workspace API key by name. This endpoint is destructive and requires additional account permissions, even though the documentation is public. Contact your ElevenLabs representative to enable it for your account.

Resource access disclosure: Resource access response models add optional access_source (creator, explicit, workspace_default, workspace_admin) so clients can disclose why a user has access to a shared resource.

Speech to Text

Larger upload limit: Convert speech to text now accepts audio and video files up to 5.0GB, increased from 3.0GB.

Dubbing

hCaptcha support: Dub a video or audio file request body adds optional hcaptcha_token (string) for bot protection on dubbing project creation.

Zip render format: RenderType adds zip alongside existing output formats such as mp4, aac, mp3, wav, aaf, tracks_zip and clips_zip.

SDK Releases

Packages

@elevenlabs/[email protected] - Added configurable microphone input chunk duration via inputChunkDurationMs (default 25ms).

@elevenlabs/[email protected] - Exposed inputChunkDurationMs for microphone input chunk duration and updated the client dependency to @elevenlabs/[email protected].

@elevenlabs/[email protected] - Updated dependencies to @elevenlabs/[email protected] and @elevenlabs/[email protected].

@elevenlabs/[email protected] and @elevenlabs/[email protected] - Updated widget dependencies to @elevenlabs/[email protected].

Flutter SDK v0.6.1 - Hardened LiveKit session teardown against uncaught stream errors.

API

Original source

Introducing Speech Engine

ElevenLabs Speech Engine adds real-time voice to your own chat agent or LLM. ElevenLabs handles speech-to-text, turn-taking, text-to-speech and browser playback while your server owns the agent logic and streams response text over a Speech Engine WebSocket. Use it when you want voice on a custom runtime rather than a fully hosted ElevenAgents configuration.

ElevenAgents

• Text behavior overrides: Added text_behavior_overrides, a per-ConversationInitiationSource map of BehaviorOverride objects with optional verbosity, output_format and interaction_budget fields for channel-specific agent behavior.
• Integration sources: Added Intercom, Telegram and Freshdesk.
• OTLP conversation traces: Get conversation details now accepts an optional format query parameter. Set format=otlp_traces to return OTLP-compatible trace data alongside the standard conversation payload.
• ASR keyword overrides: Added ASRConversationalConfigOverride and ASRConversationalConfigOverrideConfig schemas with optional keywords arrays, wired into conversation config client override models.
• Webhook auth metadata: Webhook tool configuration schemas now expose optional auth_resolved_params (string array) documenting URL placeholders resolved from the auth connection.

Music

• Generation mode: Added MusicGenerationMode (track, loop, ambience) and an optional generation_mode field on music prompt request bodies.
• Video to music model: Video to music (POST /v1/music/video-to-music) now accepts optional model_id (string, default music_v1).

ElevenCreative Studio

• Conversion credits: Chapter and voice conversion statistics response models now include optional credits_needed_to_convert (integer) indicating credits required before conversion.

Workspaces

• Resource types: Added studio_projects to WorkspaceResourceType.

SDK Releases

Python SDK

• v2.50.0 - Regenerated the SDK for the May 25, 2026 API schema.
• v2.49.1 - Updated Speech Engine API calls to return the full response object.
• v2.49.0 - Regenerated the SDK for the May 18–25, 2026 API schema, including ElevenAgents text behavior overrides, music generation_mode, and workspace studio_projects.

JavaScript SDK

• v2.50.0 - Added missing Music API methods and tests, and regenerated the SDK for the May 25, 2026 API schema.
• v2.49.1 - Updated Speech Engine API calls to return the full response object.
• v2.49.0 - Regenerated the SDK for the May 18–25, 2026 API schema, including ElevenAgents text behavior overrides, music generation_mode, and workspace studio_projects.

Packages

• @elevenlabs/[email protected] - Fixed iOS Safari dropping the first agent message on WebSocket voice sessions by unlocking an AudioContext on the first user gesture and priming the playback graph after the audio worklet loads.
• @elevenlabs/[email protected] and @elevenlabs/[email protected] - Style emotion and audio tags in voice transcripts when strip_audio_tags is off, and treat null top-level terms_html or terms_text as a kill switch for the terms and conditions modal.
• @elevenlabs/[email protected] and @elevenlabs/[email protected] - Updated widget dependencies to @elevenlabs/[email protected].

API

Original source

ElevenAgents

Agent version metadata: Added an API endpoint to retrieve metadata for a specific agent version. The response includes the version ID, agent ID, branch ID, description, sequence number, commit timestamp, parents and access information.

Conversation filtering: Added a text_only filter to conversation list and message text search endpoints so developers can narrow results to text-only conversations.

Procedure loading: Added load_procedure as a system tool configuration with ProcedureAtVersion, and added skills to ProcedureCompilerMode. ProcedureSettings.compiler_mode now defaults to skills.

Agent configuration updates: Added gemini-3.1-flash-lite and qwen35-397b-a17b as LLM options, added genesys_bot_connector as a conversation initiation source, added auto_resolve_after_inactive_minutes to alerting settings, and added attributes_to_headers to SIP trunk configuration.

Custom LLM temperature: Agent prompt temperature can now be set to null to omit the temperature field from downstream LLM requests.

Workspaces

Auth connection updates: Added an API endpoint to update workspace auth connections. The endpoint supports updating basic auth, OAuth2 client credentials and OAuth2 JWT connections. OAuth2 client credentials now support custom_headers for token requests.

Auth connection types: Added bearer auth create request support and Slack bot auth response schemas.

Workspace resource types: Added convai_templates and transcription_tasks to workspace resource types.

Voice Isolator

Video processing status: Audio isolation history items now include the video_processing_failed boolean field.

SDK Releases

Python SDK

v2.48.0 - Regenerated the SDK for the May 18, 2026 API schema, including typed support for workspace auth connection updates, agent version metadata, conversation text_only filters, new ElevenAgents configuration fields, updated LLM options and voice isolator history updates. The release also excludes the speech_engine_custom.py example from Fern packaging.

JavaScript SDK

v2.48.0 - Added environment configuration to conversation initiation data and events, and regenerated the SDK for the May 18, 2026 API schema, including workspace auth connection updates, agent version metadata, conversation text_only filters, new ElevenAgents configuration fields, updated LLM options and voice isolator history updates.

Packages

@elevenlabs/[email protected], @elevenlabs/[email protected], @elevenlabs/[email protected], @elevenlabs/[email protected] and @elevenlabs/[email protected] - Updated the client dependency. @elevenlabs/[email protected] pins livekit-client to 2.16.1 and forces the dual peer connection path to fix WebRTC connection failures with newer LiveKit join protocols.

@elevenlabs/[email protected] - Removed manually maintained types from @elevenlabs/types, including Role, Mode, Status, Callbacks, CALLBACK_KEYS, DisconnectionDetails, MessagePayload and AudioAlignmentEvent. Import those types from @elevenlabs/client instead. The types package now contains only generated code.

iOS SDK

v3.2.0 - Added support for text-only conversations over WebSockets and fixed message handling.

v3.1.5 - Improved ConnectionManager and DataChannelReceiver cleanup on deallocation, skipped audio hardware initialization in text-only mode, removed unused code and duplicate agent ID extraction, and bumped visionOS support.

API

Original source

ElevenAgents

SIP logs: SIP signaling logs are now available for SIP trunk calls in conversation history and phone number settings. Logs include the SIP call ID, phone numbers, addresses, transport, message direction, raw messages and errors to help debug call setup and routing issues.

Knowledge base document updates: New API to list indexed (RAG) chunks for a document. Documents can also be edited in place: rename the item and, for text-based documents, update the body without re-uploading the file. (File-based documents still use the existing replace-file flow where applicable.)

SMS conversation metadata: Added SMS support to conversation metadata with SMSConversationInfo, sms as an authorization method and twilio_sms as a conversation initiation source.

Agent configuration updates: Added background music configuration schemas, alerting monitor configuration, 2D layout fields, widget file upload configuration, and new LLM options gpt-5.4-mini, gpt-5.4-nano, gpt-5.4-mini-2026-03-17 and gpt-5.4-nano-2026-03-17.

Workspaces

API request analytics: Added a workspace analytics endpoint for querying API requests with time range, filtering, search, sort and limit controls.

API key IP allowlisting: Added allowed_ips to service account API key create, edit and response schemas. Create requests accept an array of IP addresses or CIDR ranges, or null to allow all IPs. Edit requests also accept clear and no_update.

Workspace permissions: Added conversational_ai_read and voice_design to workspace group permissions.

Voice Design

Voice preview migration: Deprecated POST /v1/text-to-voice/create-previews. Use Design a voice to create previews, then use the returned generated_voice_id when creating a voice.

Voice Changer

WAV output formats: Added wav_8000, wav_16000, wav_22050, wav_24000, wav_32000, wav_44100 and wav_48000 to the output_format query parameter on speech-to-speech conversion.

SDK Releases

Python SDK

v2.47.0 - Regenerated the SDK for the May 12, 2026 API schema. The release adds typed support for RAG chunk listing, file document updates, workspace API request analytics, service account API key IP allowlisting, phone number agent configuration fields, webhook request headers, voice metadata moderation, new LLM options and updated speech-to-speech output formats.

JavaScript SDK

v2.47.0 - Regenerated the SDK for the May 12, 2026 API schema. The release adds typed support for RAG chunk listing, file document updates, workspace API request analytics, service account API key IP allowlisting, phone number agent configuration fields, webhook request headers, voice metadata moderation, new LLM options and updated speech-to-speech output formats.

Packages

@elevenlabs/[email protected], @elevenlabs/[email protected], @elevenlabs/[email protected] and @elevenlabs/[email protected] - Added full tool result payload support to onAgentToolResponse. The callback now receives agent_tool_response_full_payload events with the raw full_tool_result string, capped at 64 KB, when enabled in the agent configuration.

@elevenlabs/[email protected], @elevenlabs/[email protected], @elevenlabs/[email protected] and @elevenlabs/[email protected] - Added native mute and unmute support to Scribe realtime STT. RealtimeConnection now exposes mute(), unmute() and isMuted, and useScribe exposes matching state and callbacks. The releases also add onAgentResponseCorrection for agent response correction events.

@elevenlabs/[email protected], @elevenlabs/[email protected], @elevenlabs/[email protected] and @elevenlabs/[email protected] - Added optional contextId to sendContextualUpdate for deduplicating contextual updates and added llm to the typed agent prompt override for conversation sessions. The React package also allows useScribe microphone deviceId to use full ConstrainDOMString constraints.

@elevenlabs/[email protected] and @elevenlabs/[email protected] - Added file upload support to the embedded ElevenAgents widget.

@elevenlabs/[email protected] and @elevenlabs/[email protected] - Fixed text input submission for IME users by ignoring Enter keydowns while composition is active.

@elevenlabs/[email protected] and @elevenlabs/[email protected] - Updated the widget packages to @elevenlabs/[email protected], including full tool result payload support.

@elevenlabs/[email protected] and @elevenlabs/[email protected] - Fixed transcript ordering when user and agent messages share the same event_id, so voice and DTMF turns render the user transcript before the agent message.

@elevenlabs/[email protected] and @elevenlabs/[email protected] - Fixed voice widget transcripts so streamed agent response parts are ignored for voice sessions and late user transcripts are inserted before their matching agent response.

API

Original source

ElevenAgents

Conversation tags: Added first-class conversation tags for organizing and filtering conversations. You can now create, update, list and delete tags, assign tags to conversations, and filter conversation history by tag_ids.

Conversation list filters: Added exclude_statuses to list conversations, allowing clients to hide conversations with statuses such as initiated, in-progress, processing, done, or failed.

Model options: Added claude-opus-4-7, gpt-5.4, gpt-5.5, gpt-5.4-2026-03-05, gpt-5.5-2026-04-23, and qwen36-35b-a3b to the LLM enum.

Contextual update metadata: Added contextual_update_info to conversation transcript response items. The field references ContextualUpdateInfo, which includes context_id and is_superseded, so clients can identify contextual updates and whether they have been replaced by later context.

Batch calling filter: Added an optional agent_id query parameter to list workspace batch calling jobs, allowing clients to return jobs for a single agent.

Test invocation listing: Made the agent_id query parameter optional and nullable on list test invocations, allowing clients to list test invocations without filtering by one agent.

MCP response timeout: Increased the maximum response_timeout_secs value from 120 to 300 seconds on MCP server configuration and MCP tool configuration overrides.

Workspaces

Subscription overage: Added current_overage to SubscriptionResponseModel and ExtendedSubscriptionResponseModel.

Resource collections: Added resource_collection to the WorkspaceResourceType enum.

ElevenCreative Studio

Project image status: Added error and pending_task to ProjectImageResponseModel, and made signed image URLs nullable when an image is still processing or has failed.

Pending media fields: Removed legacy pending_block_ids and pending_external_audio_ids fields from project external audio and video response models.

SDK Releases

Python SDK

v2.46.0 - Added keyterms and no_verbatim support to the Scribe realtime API, refactored WebSocket URL construction, and regenerated the SDK for the May 7, 2026 API schema, including conversation tags, conversation list filters, batch calling agent_id filtering, optional test invocation agent_id, contextual update metadata, and MCP response timeout updates.

JavaScript SDK

v2.46.0 - Fern regeneration for the May 7, 2026 API schema, including conversation tags, conversation list filters, batch calling agent_id filtering, optional test invocation agent_id, contextual update metadata, and MCP response timeout updates.

Packages

@elevenlabs/[email protected] - Added keyterms (string[]) and noVerbatim (boolean) options to the Scribe realtime API. keyterms are sent as repeated WebSocket query parameters and can include up to 50 terms of up to 20 characters each. noVerbatim removes filler words, false starts, and disfluencies from transcripts. Also fixed a case where interruptions could cut off agent audio that arrived less than 2 seconds after the interruption.

@elevenlabs/[email protected] - Added shared types for Scribe realtime keyterms and noVerbatim.

@elevenlabs/[email protected], @elevenlabs/[email protected], @elevenlabs/[email protected], and @elevenlabs/[email protected] - Updated to the latest client package, including Scribe realtime options and the agent audio interruption fix.

@elevenlabs/[email protected] - Patch release that includes the Scribe realtime options, the agent audio interruption fix, and an automatic random user ID when none is set.

Android SDK

v0.9.0 - Added support for detecting user audio while the user is muted.

API

Original source

ElevenAgents

agent_response_complete WebSocket event: A new agent_response_complete client event fires exactly once when an agent's response is fully delivered -- after all LLM generation, tool call chains, and audio playback complete. The event lets clients reliably detect end of turn for batching messages, wake-word activation, or post-turn UI updates. The event is suppressed while async tool tasks are still running and is not emitted on agents configured with turn_timeout or soft_timeout. Added a new AGENT_RESPONSE_COMPLETE value to the ClientEvent enum and a corresponding AgentResponseCompleteClientEvent response model.

Pre-tool speech mode: Added a new pre_tool_speech field (PreToolSpeechMode enum, default auto) on MCP server configuration and per-tool overrides. Replaces the now-deprecated force_pre_tool_speech boolean. Values: auto decides whether the agent speaks before the tool call based on recent tool latency, force always asks the agent to speak, and off opts out entirely.

Tool dispatch respects execution mode: Workflow tool dispatch nodes now correctly respect each nested tool's execution_mode. If any tool in a dispatch node uses POST_TOOL_SPEECH, the workflow waits for the current turn's audio to be fully exposed before executing the dispatch.

MCP response timeout: Added a response_timeout_secs field (integer, default 30, min 5, max 120) on MCP server configuration and per-tool overrides, controlling the maximum time to wait for each MCP tool call to complete.

Agent trust context: Added a trust_context field on agent platform settings (AgentTrustContext enum: unknown | low | high, default unknown). low is for agents serving untrusted external participants, where outputs should be vetted and tool access scoped; high is for agents serving the owner where full tool access is appropriate; unknown covers agents created before this feature.

Source attribution toggle: Added a source_attribution boolean (default false) on conversation config. When enabled and knowledge base content is present, the LLM is instructed to report which sources it used.

Test sharing mode filter: The list tests endpoint now accepts a sharing_mode query parameter (all | shared_with_me, default all) to filter tests and folders to only those shared with the current user that they did not create.

Tool icons and execution metadata: Added icons (array of Icon) and execution (ToolExecution) fields to the Tool schema. Icon includes src, mimeType, and sizes for UI display, and ToolExecution.taskSupport (forbidden | optional | required) declares how the tool participates in tasks.

Procedure compiler default: The ProcedureCompilerMode default has changed from deterministic to append, and the llm value has been removed. Existing agents that explicitly set deterministic are unaffected.

RAG and knowledge base attribution metadata: Added used_static_kb_document_ids (array of strings) on ConversationHistoryTranscriptCommonModel and ConversationHistoryTranscriptResponseModel, and used_chunk_ids on RagRetrievalInfo, surfacing exactly which knowledge base documents and RAG chunks contributed to each transcript turn.

Dynamic variable refactor: dynamic_variables and dynamic_variable_placeholders now reference unified DynamicVariableValueType-Input / DynamicVariableValueType-Output schemas (replacing the prior DynamicVariableContainerValueType-* schemas), with broader support for nested and list values. DynamicVariableAssignment gained a preserve_native_type field to keep typed values rather than coercing to strings.

Audio Isolation

History endpoints: Two new endpoints expose your audio isolation history.

List audio isolation history (GET /v1/audio-isolation/history) returns a paginated list of all your audio isolation generations. Supports page_size, page, and search query parameters.

Delete audio isolation history item (DELETE /v1/audio-isolation/history/{history_item_id}) deletes a specific item and its associated media files.

Speech to Text

Realtime keyterms and verbatim mode: The Scribe realtime WebSocket now accepts a keyterms parameter (array of strings, max 50 entries of up to 20 characters each) to bias the model toward specific terms, and a no_verbatim boolean to remove filler words, false starts, and disfluencies from transcripts. Both parameters are echoed back in the session_started event. Available across the JavaScript SDK, Python SDK, and the @elevenlabs/client browser/Node client SDK.

SDK Releases

Python SDK

v2.45.0 - Fern regeneration for the April 27, 2026 API schema, including audio isolation history endpoints, tool executions, MCP pre_tool_speech and response_timeout_secs, and the agent_response_complete client event. Also includes a fix to the notebook install hint in the README.

v2.44.0 - Fern regeneration for the April 21, 2026 API schema, picking up the trust_context field, pre_tool_speech mode, asset transcription support, and MCP response timeout configuration.

JavaScript SDK

v2.45.0 - Added keyterms (string array, max 50 keyterms of up to 20 chars each) and noVerbatim (boolean) options on the Scribe realtime client. keyterms are sent as repeated query parameters on the WebSocket URL to bias transcription, and noVerbatim removes filler words and disfluencies. Both fields are also added to the typed Config interface for the session_started echo. Also includes the April 27, 2026 Fern regeneration (#376).

v2.44.0 - Fern regeneration for the April 21, 2026 API schema, picking up the trust_context field, pre_tool_speech mode, and MCP response timeout configuration.

Swift SDK

v3.1.4 - Fixed an issue where the local microphone kept publishing after an agent disconnected (silence timeout or end_call tool). onAgentDisconnected now disconnects the LiveKit room and tears down conversation state, with onDisconnect firing an .agent reason. ConnectionManaging.onAgentDisconnected is now async. Removed the unused ConversationConnectionManager wrapper.

Packages

@elevenlabs/[email protected] - Fixed the agent tool-call sound being interpreted as user speech and interrupting the agent during tool execution.

@elevenlabs/[email protected] - Added support for the upload conversation file endpoint, letting clients attach files to an in-progress conversation directly from the client SDK.

@elevenlabs/[email protected], @elevenlabs/[email protected] - Updated to @elevenlabs/[email protected] / @elevenlabs/[email protected], picking up the tool-call sound fix and conversation file upload support.

@elevenlabs/[email protected], @elevenlabs/[email protected] - Updated to the latest @elevenlabs/client for the same fixes.

@elevenlabs/[email protected], @elevenlabs/[email protected] - Updated to @elevenlabs/[email protected] for the tool-call sound fix.

@elevenlabs/[email protected], @elevenlabs/[email protected] - Updated to @elevenlabs/[email protected] for conversation file upload support.

API

Original source

Developer Resources

ElevenLabs Devs YouTube channel: A new developer-focused YouTube channel is now live, featuring tutorials, API walkthroughs, and technical deep dives to help you get the most out of the ElevenLabs platform.

ElevenAgents

Workflow starting node override: Conversations can now be started at a specific workflow node by passing starting_workflow_node_id in the conversation initiation client data. This is gated by an opt-in enable_starting_workflow_node_id_from_client field in the agent's platform override settings. When enabled, clients can specify which node to begin a conversation at, which is useful for agent memory and longer-term WebSocket use cases. If the specified node does not exist, the conversation falls back to the default entry point.

Post-call analysis LLM configuration: Agent platform settings now include an analysis_llm field (default: gemini-2.5-flash) that sets the default LLM for post-call analysis, including evaluation criteria and data collection. Individual data collection properties can override this default with a per-item llm field via the new AnalysisProperty schema, giving fine-grained control over which model processes each analysis item.

New LLM options: Added gpt-5.4 to the list of available LLM providers for agent configuration. Added xhigh to the LLMReasoningEffort enum for extended reasoning on supported models.

Null literal in workflow expressions: Workflow conditional expressions now support null comparisons via the new ASTNullNode type, enabling branches like "if variable is null" in workflow logic.

Get secret by ID: A new get secret endpoint (GET /v1/convai/secrets/{secret_id}) retrieves a single workspace secret by its ID. The list secrets endpoint also now accepts a search query parameter to filter secrets by name prefix.

Searchable phone numbers in batch calling: The batch calling form in the dashboard now includes a searchable phone number selector, making it easier to find the right outbound number when configuring batch calls.

Speech to Text

Speaker role detection: The convert speech to text endpoint now accepts a detect_speaker_roles parameter (boolean, default false). When enabled alongside diarize=true, speaker labels are returned as agent and customer instead of speaker_0, speaker_1. This cannot be used with use_multi_channel=true. Usage incurs an additional 10% surcharge on the base transcription cost.

Text to Dialogue

Input character limit guidance: The text to dialogue endpoints now document a recommended limit of 2,000 characters across all inputs[].text values per request. Longer requests may terminate early in streaming responses or return a validation error.

Workspaces

Usage analytics endpoint: A new usage by product over time endpoint (POST /v1/workspace/analytics/query/usage-by-product-over-time) returns credit usage broken down by product type over time. Results are returned in a tabular structure with configurable interval_seconds, group_by dimensions, and filters. The previous GET /v1/usage/character-stats endpoint has been deprecated in favor of this new endpoint.

SDK Releases

Packages

@elevenlabs/[email protected] - Fixed conversation startup readiness so onConnect runs after the session is marked connected and React has synchronized conversationRef. Also exposed and forwarded onConversationCreated for consumers that need the created Conversation instance before onConnect.

@elevenlabs/[email protected] - Fixed conversation startup readiness and exposed onConversationCreated callback, matching the @elevenlabs/[email protected] changes.

@elevenlabs/[email protected], @elevenlabs/[email protected], @elevenlabs/[email protected] - Updated to @elevenlabs/[email protected] with conversation startup fixes.

API

Original source

ElevenAgents

Conversation topic discovery: A new conversation topics endpoint (GET /v1/convai/agents/{agent_id}/topics) returns the latest topic discovery results for a given agent, surfacing recurring themes across conversations. The list conversations endpoint now accepts a topic_ids query parameter to filter conversations by discovered topic.

Knowledge base content search: A new search knowledge base endpoint (GET /v1/convai/knowledge-base/search) provides fuzzy text search over knowledge base document content. Results include highlighted snippets with SearchHighlightSegment objects and support cursor-based pagination with configurable page sizes (up to 100, default 30). Filter by document type with the optional types parameter.

Flexible branch merging: The merge branch endpoint no longer restricts merges to the main branch -- any branch can now be used as a merge target. A new optional force boolean parameter overrides timestamp-based conflict resolution when set to true. Branch metadata responses now include parent_branch_id and merged_from_version_id for better lineage tracking.

Secret dependency management: A new get secret dependencies endpoint (GET /v1/convai/secrets/{secret_id}/dependencies/{resource_type}) returns paginated dependency lookups filtered by resource type (tools, agents, or phone_numbers). The list secrets endpoint now accepts a dependency_limit query parameter to control how many dependencies are previewed per secret, with agents_has_more, tools_has_more, and phone_numbers_has_more flags indicating when additional dependents exist beyond the preview.

New LLM options: Added gemini-3.1-pro-preview, qwen35-35b-a3b, and qwen35-397b-a17b to the list of available LLM providers for agent configuration.

Voices

Non-community voice filter: The voice_type query parameter on the list voices endpoint now accepts non-community, which returns personal and workspace voices combined while excluding library copies. This provides a convenient filter for teams that want to see only their own voices without community-shared ones.

SDK Releases

Python SDK

v2.43.0 - Fern regeneration for the April 13, 2026 API schema, including knowledge base content search, conversation topics, flexible branch merging, and new LLM providers.

JavaScript SDK

v2.43.0 - Fern regeneration for the April 13, 2026 API schema, including knowledge base content search, conversation topics, flexible branch merging, and new LLM providers.

Swift SDK

v3.1.3 - Reduced background noise detection in software muted VAD, preventing false voice activity triggers when the microphone is muted.

Packages

@elevenlabs/[email protected] - Fixed getInputVolume() and getOutputVolume() returning 0 in React Native by adding native volume providers using LiveKit's RMS and multiband FFT processors. getInputByteFrequencyData() and getOutputByteFrequencyData() now return data focused on the human voice range (100-8000 Hz), which is more useful for voice visualization, and on web getInputVolume() and getOutputVolume() are also computed from this range.

@elevenlabs/[email protected] - Fixed startSession errors being swallowed instead of surfaced via onError in ConversationProvider. Previously, when Conversation.startSession() rejected (e.g., "agent not found"), the UI would get stuck in "connecting" with no error feedback.

@elevenlabs/[email protected] - Updated to @elevenlabs/[email protected] and @elevenlabs/[email protected] with native volume provider fixes.

@elevenlabs/[email protected] - Fixed transcript message ordering in voice mode where agent responses could appear before user messages.

API

Original source

ElevenAgents

• Scoped conversation analysis: Evaluation criteria and data collection items can now be scoped to conversation (full transcript) or agent (only the portion where a specific agent was active). Added scope field to PromptEvaluationCriteria, data_collection_scopes to agent platform settings, and a new scoped array of ScopedAnalysisResult on the conversation analysis response. This is particularly useful for multi-agent workflows where each agent should be evaluated independently.
• Agent test folder management: Tests can now be organized into folders. New endpoints for creating, retrieving, updating, and deleting test folders, plus bulk moving tests between folders.
• Tool and knowledge base overrides in workflows: Agent workflow node overrides now support tool_ids and knowledge_base fields in PromptAgentAPIModelOverrideConfig, allowing workflow nodes to control which tools and knowledge base documents each sub-agent can access.
• Response filter hide_all mode: Added hide_all option to ResponseFilterMode, forcing the system to hide all fields of a tool response from the agent.
• Visited agents in conversation history: The get conversation response now includes a visited_agents array of VisitedAgentRef objects (with agent_id and branch_id), tracking which agents participated in a multi-agent conversation.
• Multimodal message support in hooks: The useConversationControls hook now exposes sendMultimodalMessage, and the MultimodalMessageInput type is exported from @elevenlabs/client, making it easier to send images and other multimodal content during conversations.

Speech to Text

• Audio duration in responses: The convert speech to text response now includes an audio_duration_secs field, providing the total duration of the transcribed audio without requiring client-side calculation.

Voices

• Recording quality and review status: The get voice response now includes recording_quality (enum: studio, good, ok, poor, bad) and labelling_status (enum: in_review, review_complete) fields, providing visibility into voice quality assessment.

SDK Releases

JavaScript SDK

• v2.42.0 - Fern regeneration for the April 7, 2026 API schema, including scoped analysis, test folders, and DTMF input support.

Python SDK

• v2.42.0 - Fern regeneration for the April 7, 2026 API schema, including scoped analysis, test folders, and DTMF input support.

Swift SDK

• v3.1.2 - Fixed ObjC category dispatch for LiveKit delegate methods, resolving potential crashes in Swift-based voice agent integrations.

Packages

• @elevenlabs/[email protected] - Exposed sendMultimodalMessage in the client API and exported the MultimodalMessageInput type for sending images and other multimodal content during conversations.
• @elevenlabs/[email protected], @elevenlabs/[email protected], @elevenlabs/[email protected], @elevenlabs/[email protected] - Fixed Node.js ESM compatibility by adding explicit .js extensions to all relative imports and setting "type": "module" on @elevenlabs/types.
• @elevenlabs/[email protected] - Added automatic language selection from localStorage history and browser language preferences for the embeddable widget.

API

Original source

ElevenAgents

MCP tool scoping in agent workflows:

Agent workflow nodes can now restrict which MCP tools a sub-agent is permitted to call. When tool inheritance is disabled on a node, only the explicitly selected MCP tools are loaded for that sub-agent, giving teams precise control over tool access per workflow step.

Conversation file uploads:

The create agent and update agent endpoints now support a file_input field on ConversationConfig. When enabled, end users can attach images or PDFs in chat (requires an LLM with multimodal input support). Configurable with enabled (boolean) and max_files_per_conversation (integer).

Re-run conversation analysis:

New run conversation analysis endpoint (POST /v1/convai/conversations/{conversation_id}/analysis/run) re-evaluates a completed conversation using the agent's current evaluation criteria and data collection settings, without needing a new call.

Tool response mocking for tests:

Agent simulation tests and test suite invocations now support a tool_mock_config field to control how tool calls are handled during testing. Use MockingStrategy (all, selected, none) to choose which tools are mocked and MockNoMatchBehavior (call_real_tool, raise_error) to set the fallback when no mock matches.

Text search sort order:

The text search conversations endpoint now accepts a sort_by query parameter with values search_score (default) or created_at, allowing you to control whether results are ordered by relevance or recency.

mTLS auth connections:

Agent auth connections now support mutual TLS (mtls) as an auth_type, in addition to the existing options. New CreateMTLSAuthRequest and MTLSAuthResponse schemas are available for creating and retrieving mTLS-authenticated connections.

Max duration message:

Added max_conversation_duration_message field to agent configuration. When set to a non-empty string, the agent will send this message to the user when the maximum conversation duration is reached.

Branch and environment in conversation initiation:

Added branch_id and environment optional fields to the conversation initiation client data (ConversationInitiationClientDataRequest) and submit batch call request body, enabling routing to specific agent branches and environments.

Music

Video to music:

New POST /v1/music/video-to-music endpoint generates background music from one or more video files. Videos are combined in sequence. Accepts optional description (up to 1,000 characters) and tags (up to 10 style tags such as upbeat or cinematic) to influence the generated track.

Speech to Text

Transcribe from URL:

The convert speech to text endpoint now accepts a source_url parameter (string, optional) for transcribing audio or video from a hosted URL, including YouTube videos, TikTok videos, and other video hosting services. This can be used as an alternative to uploading a file directly.

Voices

Total count in shared voices list:

The list shared voices response now includes a total_count field, making it easier to implement pagination and display result counts.

SDK Releases

JavaScript SDK

• v2.41.0 - Added support for the multimodal_message WebSocket event type in ElevenAgents real-time conversations. Includes Fern regeneration for the latest API schema updates.
• v2.41.1 - Fern regeneration to match the April 1, 2026 API schema.

Python SDK

• v2.41.0 - Fixed audio_interface to be optional in text-only conversation mode, resolving a runtime error when starting a session without audio. Includes Fern regeneration for the latest API schema.

Packages

This release includes the new v1.0.0 of the client side Agent SDKs. It features major breaking changes to @elevenlabs/client, @elevenlabs/react, and @elevenlabs/react-native. Review the migration guidance below before upgrading.

To help upgrade, we released a Skill to help your agents upgrade for you. Install it with

npx skills add elevenlabs/packages

You can read more about the v1 release and its improvements on our developer blog.

@elevenlabs/[email protected] — Breaking changes:

Input and Output classes are no longer exported. Use the InputController and OutputController interfaces from @elevenlabs/client instead.

Conversation is no longer a class — it is now a namespace object and a type alias for TextConversation | VoiceConversation. Remove any instanceof Conversation checks and subclasses.

The default connectionType is now inferred from the conversation mode: voice conversations use "webrtc" by default, and text-only conversations use "websocket". To keep the previous behavior for voice, pass connectionType: "websocket" explicitly.

VoiceConversation.wakeLock is now private. Pass useWakeLock: false in session options to suppress wake lock management.

changeInputDevice() and changeOutputDevice() now return Promise<void> instead of Promise<Input> or Promise<Output>.

Replace conversation.input.analyser.getByteFrequencyData(data) with conversation.getInputByteFrequencyData().

Replace conversation.input.setMuted(v) with conversation.setMicMuted(v).

Replace conversation.output.gain.gain.value = v with conversation.setVolume({ volume: v }).

getInputVolume(), getOutputVolume(), getInputByteFrequencyData(), and getOutputByteFrequencyData() now return 0 or an empty Uint8Array instead of throwing when no conversation is active.

@elevenlabs/[email protected] — Breaking changes:

useConversation now requires a ConversationProvider ancestor. Wrap your component tree in <ConversationProvider> and move options to the provider or to the hook.

DeviceFormatConfig and DeviceInputConfig exports are removed. Use FormatConfig and InputDeviceConfig from @elevenlabs/client instead.

New granular hooks replace the monolithic useConversation for better render performance: useConversationControls(), useConversationStatus(), useConversationInput(), useConversationMode(), useConversationFeedback(), and useRawConversation(). Each hook subscribes only to the state it needs, preventing unnecessary re-renders.

New useConversationClientTool(name, handler) hook for registering client tools that agents can invoke, with automatic cleanup on unmount.

Added controlled mute support via isMuted and onMutedChange props on ConversationProvider.

@elevenlabs/[email protected] — Breaking changes:

The previous ElevenLabsProvider and useConversation API have been removed and replaced with re-exports from @elevenlabs/react. Replace ElevenLabsProvider with ConversationProvider and useConversation with the granular hooks (useConversationControls, useConversationStatus, etc.).

On React Native, the package now polyfills WebRTC globals, configures the native AudioSession, and registers a platform-specific voice session strategy on import.

@elevenlabs/[email protected]

• Exports the CALLBACK_KEYS runtime array containing all keys from the Callbacks interface, used internally by the React SDK for callback composition.

@elevenlabs/[email protected]

• Added the guardrail_triggered server-to-client WebSocket event and the onGuardrailTriggered callback, which fires when the server detects a guardrail violation during a conversation. Also added type discriminants to TextConversation and VoiceConversation to enable discriminated union narrowing, and added startSession overloads that narrow the return type based on the textOnly option.

@elevenlabs/[email protected]

• Added the guardrail_triggered WebSocket event and onGuardrailTriggered callback, consistent with @elevenlabs/[email protected].

@elevenlabs/[email protected]

• Added client-side support for mocking tool responses in agent conversations, enabling test scenarios that simulate tool call outcomes without invoking real tools.

@elevenlabs/[email protected]

• Added type definitions for tool response mocking in agent conversations.

@elevenlabs/[email protected]

• Updated to depend on @elevenlabs/[email protected].

@elevenlabs/[email protected]

• Updated to depend on @elevenlabs/[email protected] and @elevenlabs/[email protected].

API

Original source