Eleven Labs Release Notes

Agents Platform

• Widget end-call feedback: Widgets now support customizable end-of-call feedback collection with optional rating and comment fields, enabling you to gather user feedback directly within your agent conversations.
• Soft timeout configuration: Added comprehensive soft timeout settings to control how agents handle pauses in conversation, with configurable prompts and behavior across turn and conversation levels.
• Advanced conversation filtering: The conversations endpoint now supports filtering by call duration range, evaluation parameters, data collection parameters, and specific tool names.
• Enhanced conversation feedback: Updated conversation feedback system with structured feedback types including ratings and comments for better user experience tracking.

Studios

• Extended project metadata: Projects now include comprehensive asset tracking with video thumbnails, external audio references, and enhanced snapshot information including audio duration.

Billing

• Enhanced invoice details: Invoice responses now include detailed discount information with a new discounts array, replacing the deprecated discount_percent_off and discount_amount_off fields. The subtotal_cents and tax_cents fields provide clearer invoice breakdowns.

Music API

• Stem separation latency improvements: The stem separation endpoint has been updated to better handle audio files and provide more predictable latency for processing requests.

SDK Releases

JavaScript SDK

• v2.23.0 - Updated Speech to Text (Scribe) endpoint to scribe_realtime and exported additional TypeScript types for improved developer experience.
• v2.22.0 - Updated with latest API schema changes including conversation filtering, soft timeout configuration, and widget feedback features.

Python SDK

• v2.22.1 - Updated Speech to Text (Scribe) endpoint to scribe_realtime and fixed circular import issues for improved stability.
• v2.22.0 - Updated with latest API schema changes including conversation filtering, soft timeout configuration, and widget feedback features.

Android SDK

• v0.5.0 - Added setVolume and getVolume functions for programmatic audio control, with example implementation including a volume seek bar in the sample app.

Agents Packages

• @elevenlabs/[email protected] - Updated realtime endpoint configuration and improved documentation.
• @elevenlabs/[email protected] - Updated realtime endpoint configuration and improved documentation.
• @elevenlabs/[email protected] - Updated type definitions to match latest API schema changes.
• @elevenlabs/[email protected] - Minor bug fixes and stability improvements.
• @elevenlabs/[email protected] - Updated widget embed functionality with end-call feedback support.
• @elevenlabs/[email protected] - Added end-call feedback configuration to widget core.
• @elevenlabs/[email protected] - Added support for customizable end-of-call feedback collection.
• @elevenlabs/[email protected] - Introduced WidgetEndFeedbackConfig and WidgetEndFeedbackType for feedback handling.
• @elevenlabs/[email protected] - Updated client configuration with latest API changes.

API

• View API changes

Original source Report a problem

UI

• Improved notifications: Updated notification system to display notifications relevant to the active platform you’re viewing, providing a more focused and contextual experience.

Agents Platform

• Dynamic variable transfer destinations: Agent transfers now support dynamic variables for phone numbers and SIP URIs, enabling runtime-determined transfer destinations based on conversation context.
• MCP tool configuration overrides: Added the ability to create, update, retrieve, and delete custom configuration overrides for specific MCP Server tools, allowing fine-grained control over tool behavior and parameters.

Text to Dialogue

• Timestamps and voice segments: Text to Dialogue now supports timestamped outputs with character-level alignment and voice segment tracking, making it easier to synchronize dialogue with animations or subtitles.

Music API

• Stem separation: Added new stem separation endpoint to isolate different audio components (vocals, drums, bass, instruments) from existing music tracks.
• Increased prompt length: Music generation now supports prompts up to 4,100 characters, with individual lyric lines supporting up to 200 characters.

Security

• Single-use tokens: Introduced time-limited single-use token generation for secure operations, providing enhanced security for sensitive API operations.

SDK Releases

JavaScript SDK

• v2.22.0 - Updated with latest API schema changes including workspace model approvals and MCP tool configuration endpoints.
• v2.21.0 - Added support for intercepting raw WebSocket messages via a general message handler, allowing developers to access all messages beyond the standard callbacks, including undocumented message types like agent_tool_response.

Python SDK

• v2.22.0 - Updated with latest API schema changes including workspace model approvals and MCP tool configuration endpoints.
• v2.21.0 - Replaced print statements with proper logging to support better debugging and production use cases.

Agents Packages

• @elevenlabs/[email protected] - Package deprecated in favor of the unified ElevenLabs CLI.
• @elevenlabs/[email protected] - Fixed issue where end_call tool wasn’t properly ending conversations, and improved React Native reconnection logic after manual disconnection.
• @elevenlabs/[email protected] - Fixed issue where end_call tool wasn’t properly ending conversations, and improved reconnection logic after manual disconnection.
• @elevenlabs/[email protected] - Fixed issue where end_call tool wasn’t properly ending conversations, and improved React Native reconnection logic.

Android SDK

• v0.4.0 - Improved type safety by using ConversationMode enums instead of strings, migrated from LiveData to StateFlow with backward compatibility support, and fixed bug where agents wouldn’t end calls when requested.

iOS SDK

• v2.0.16 - Fixed issue where the end_call tool wasn’t properly ending conversations, ensuring agents can correctly terminate calls.

CLI

• @elevenlabs/[email protected] - Removed --env flag support for virtual environment isolation. This feature will be reintroduced once proper environment isolation is supported in the product.

API

TLS

Our TLS endpoints no longer allow some older and insecure cipher modes. Most clients should not be affected as they already negotiate a modern cipher mode.

View API changes

Original source Report a problem

Workspaces

• External voice sharing controls: External voice sharing and Voice Library publishing can now be disabled via workspace groups. Internal (in-organization) voice sharing is not impacted.

Agents Platform

• Multi-environment agent management: The Agents CLI now supports the --env flag, allowing you to manage agents deployed to multiple accounts simultaneously.
• Search functionality: Added search parameter to the Get conversations endpoint for filtering conversations.

SDK Releases

JavaScript SDK

• v2.20.1 - Fixed Music API type definitions and added Realtime Scribe language code support
• v2.20.0 - Added helper methods for Realtime Scribe with improved ASR capabilities. This is a beta feature and not widely available yet

Python SDK

• v2.20.1 - Fixed file parameter handling in client methods
• v2.20.0 - API schema updates and improvements
• v2.19.0 - Added helper method for Scribe Realtime with improved ASR capabilities. This is a beta feature and not widely available yet

Agents CLI

• @elevenlabs/[email protected] - Added support for --env flag to manage agents across multiple accounts, plus bug fixes and reliability improvements

React Native

• @elevenlabs/[email protected] - Removed build script and postinstall steps for improved installation experience

React

• @elevenlabs/[email protected] - Removed build script and postinstall steps for improved installation experience

Client

• @elevenlabs/[email protected] - Removed build script and postinstall steps for improved installation experience

API

• View API changes

Original source Report a problem

Agents Platform

• LLM overrides: Added support for overriding an agent’s LLM during a conversation, enabling you to specify a different language model on a per-conversation basis. This is useful for testing different models or accommodating specific requirements while maintaining HIPAA and data residency compliance.
• Post-call webhook failures: Added the option to send post-call webhook events in the event of a phone call failure. This allows you to track and respond to failed call attempts through your webhook endpoint, providing better visibility into call issues.

SDK Releases

Python SDK

• v2.18.0 - Added support for streaming, Music API inpainting, and Agent Workflows

JavaScript SDK

• v2.19.0 - Added support for Music API inpainting and Agent Workflows
• v2.18.0 - API schema updates

Client Packages

• @elevenlabs/[email protected] - Significantly reworked agents pull command with bugfixes and improvements
• @elevenlabs/[email protected] - Fixed import issues
• @elevenlabs/[email protected] - Fixed onConnect timing
• @elevenlabs/[email protected] - Reverted change to ICE transport policy
• @elevenlabs/[email protected] - Fixed import issues

Original source Report a problem

Agents Platform

• Gemini 2.5 Flash Preview models: Added support for gemini-2.5-flash-preview-09-2025 and gemini-2.5-flash-lite-preview-09-2025 LLM models, providing access to the latest September 2025 preview versions of Google’s Gemini 2.5 Flash models.
• Claude Sonnet 4.5: Added support for claude-sonnet-4-5 and claude-sonnet-4-5@20250929 models, enabling access to the latest Claude Sonnet 4.5 model released on September 29, 2025.
• Test invocations listing: Added new GET /v1/convai/test-invocations endpoint to list all test invocations with pagination support. Includes agent_id filter, page_size parameter (default 30, max 100), and cursor for pagination. Response includes test run counts, pass/fail statistics, and titles.
• Agent archiving: Added archived field (boolean, default false) to agent platform settings, allowing agents to be archived without deletion while keeping them out of active agent lists.
• MCP Server interruption control: Added disable_interruptions field (boolean, default false) to MCP server configuration, preventing user interruptions during tool execution for more reliable tool completion.
• Streaming agent responses: Added agent_chat_response_part WebSocket event type for receiving partial agent chat responses in real-time during streaming conversations.
• Workflow edge ordering: Added edge_order field (array of strings) to all workflow node types, enabling explicit control over edge evaluation order for deterministic workflow execution.
• Test suite agent tracking: Added agent_id field (string, nullable) to test invocation responses for associating test runs with specific agents.

Voice Management

• Voice generation source tracking: Added VoiceGeneration as a new source type in the History API for tracking audio generated from voice generation features.

Telephony

• SIP trunk TLS validation: Added remote_domains field (array of strings, nullable) to SIP trunk configuration for specifying domains used in TLS certificate validation.

SDK Releases

• JavaScript SDK

  • v2.18.0 - Updated with latest API schema changes from October 8, 2025

• Python SDK

  • v2.17.0 - Updated with latest API schema changes and URL generation fixes from October 6, 2025

• Packages
  All packages updated with latest API schema changes:

  • @elevenlabs/[email protected] - Updated TypeScript types and API client with new fields for agent archiving, MCP server configuration, and test invocations
  • @elevenlabs/[email protected] - Updated React hooks and components with support for new agent settings and WebSocket events
  • @elevenlabs/[email protected] - Core client library updated with new endpoint for test invocations listing and reorganized SDK method paths for secrets management
  • @elevenlabs/[email protected] - CLI tool updated with support for new agent archiving flag and test invocation commands

MCP Server

• v0.9.0 - Added option to return MCP server results as resource items for better integration with resource-based workflows

API

• View API changes

Original source Report a problem

The eleven_monolingual_v1 and eleven_multilingual_v1 models are deprecated and will be removed on December 15th, 2025. Please migrate to newer models for continued service.

Agents Platform

• Workflow Expressions: Workflows now support complex expressions that allow for defining deterministic conditions using logical operators, dynamic variables and LLM evaluation. This enables more sophisticated agent logic and decision-making capabilities.
• MCP Server Interrupt Control: Added option to disable interruptions during all tool calls for MCP Servers, providing better control over agent behavior during tool execution.
• Audio Alignment Data: Agents now have a flag to enable alignment data in audio events, useful for audio-text synchronization use cases such as lip sync applications.
• Ignore Default Personality Setting: The Agents Platform configuration page now includes a checkbox to toggle whether agents should ignore the default helpful personality, giving developers more control over agent behavior.

Speech to Text

• Fixed Base64 Encoding Flag: Resolved an issue where the is_base64_encoded flag in STT responses was incorrectly set to false for PDF and DOCX formats, even when content was actually base64 encoded.

SDK Releases

JavaScript SDK

• v2.16.0: Updated with latest API schema changes from September 19, 2025.

Packages

• @elevenlabs/[email protected]: New public TypeScript types package providing shared type definitions across ElevenLabs integrations.
• @elevenlabs/[email protected] and @elevenlabs/[email protected]: Added support for passing custom script paths to avoid blob: and data: URLs for improved security and flexibility.
• @elevenlabs/[email protected] and @elevenlabs/[email protected]: Added use_rtc attribute for widget functionality and added expand event support for better widget interaction handling.

API

View API changes

Original source Report a problem

Introducing Productions

our new managed service offering for ordering human-edited content that looks, sounds and feels natural. Made for creators and media businesses.
Our network of linguists and audio professionals offer end-to-end production quality for:
Dubbing
Captions and subtitles
Transcription
Audiobooks
You can order a project directly from the Productions page in your ElevenLabs account, or by emailing [email protected]. Pricing starts at $2/minute, contact us for more details.

Agents Platform

• MCP pre-tool speech: Added support for configuring tools extracted from an MCP Server to require pre-tool execution speech. This enhancement allows agents to provide verbal context before executing specific tools, improving the conversational flow during tool usage.
• ElevenLabs hosted LLMs: Added support for ElevenLabs hosted LLMs which unlock lower latency by running on ElevenLabs infrastructure alongside Speech to Text and Text to Speech services.
• Enum values for tool parameters: Added support for specifying a tools parameters as enum values for greater control

SDK Releases

JavaScript SDK

• v2.16.0: Updated the elevenlabs-js SDK with the latest API schema changes, including new MCP server endpoints and enhanced history filtering capabilities.

Python SDK

• v2.16.0: Updated the elevenlabs-python SDK with the latest API schema changes, including new MCP server endpoints and enhanced history filtering capabilities.
• v2.15.1: Fixed conversation handling when no authentication is required and added asyncio event loop support for better async operations.

Package Updates

• @elevenlabs/[email protected]: Updated the Agents CLI package with improvements to agent development tools. The ConvAI CLI has been renamed to Agents CLI to align with the ElevenLabs Agents Platform branding.
• @elevenlabs/[email protected]: Final release of the legacy ConvAI CLI package before migration to the new Agents CLI.
• @elevenlabs/[email protected]: Updated the React components package with enhanced functionality.

API

View API changes

Original source Report a problem