We’re excited to release Ink-2: a speech-to-text model built for real-time voice agents.

It’s ranked #1 on Artificial Analysis’s streaming leaderboard for lowest word error rate†, with the most accurate built-in turn detection of any provider, so the model knows precisely when to listen and when to respond.

For voice agents, speech-to-text has to get three things right: accuracy, turn detection, and latency. If any one of these falls short, the experience breaks down. The agent may misunderstand the user, interrupt at the wrong time, respond too slowly, or make the conversation feel unnatural. Ink-2 was built to lead on all three.

Accuracy: Getting every word right

We’ve done extensive work on structured entity recognition like phone numbers, email addresses, alphanumerics, and dates. Ink-2 understands when it’s mid-entity and waits for the full sequence before committing, with no special prompting needed.

We built Ink-2 to be robust across a range of accents, which reflects real voice agent calls. On AppTek, a multi-accent benchmark spanning 14 English accents on real call-center dialogue, Ink-2 is the strongest streaming STT provider at 8% WER, vs. 10% for Deepgram Flux and 12% for ElevenLabs Scribe v2.

Accuracy also holds under production conditions, not just clean reference audio. Our internal benchmark samples audio directly from live voice agent calls covering non-native English speakers, background noise, and degraded audio from poor network conditions. Ink-2 achieves 6.5% WER, compared to 9.2% for ElevenLabs Scribe v2 and 9.4% for Deepgram Flux.

Both structured entities and real-world production audio are where accuracy actually gets tested in a live voice agent, not just in a clean benchmark.

Turn detection: Knowing when to listen and when to respond

Accuracy shows up clearly in benchmarks, but turn detection is where most voice agents fall apart in production.

Most voice agents decide a turn is over based on silence. If someone pauses long enough, the turn abruptly ends. This works in a test environment, but on a real call it means cutting a customer off mid-address, or jumping in right after “and my email is…”

We created Ink-2 with built-in semantic endpointing: the model reads meaning, not silence, to decide when a turn is over. It knows when an incomplete address is still being given or when a trailing thought isn’t a stopping point. The turn stays open until the model is confident the speaker is done.

Ink-2 emits three events natively, with no external VAD needed:

• turn.start — the user has begun speaking
• turn.eager_end — the model predicts the turn is wrapping up; your LLM can start generating early
• turn.end — turn confirmed complete

We measure turn detection against a human-labeled reference. Precision is how often the model is right when it calls a turn over (low precision means cutting people off), and recall is how often it catches every real end-of-turn (low recall means awkward dead air while the model keeps listening). F1 balances the two into a single score.

Ink-2 holds both precision and recall high at once, while the alternatives each trade one off for the other.

Latency: Keeping the conversation flowing

Similar to TTS latency, transcription latency has a direct impact on how natural a conversation feels. The metric we care about is Time-to-Final-Transcript (TTFT): how long it takes to get a final transcript from the moment the user finishes speaking. This is what determines whether your agent feels like it’s paying attention or like it’s buffering.

Ink-2’s latency is lightning fast, with a TTFT of 0.1s. And because turn.eager_end lets your LLM get a head start before the turn is fully confirmed, your agent responds fast enough to feel like it’s actually in the conversation.

Join the teams powered by Ink-2

Ink-2 is live at play.cartesia.ai, available directly via API and across the platforms voice teams build on, including LiveKit, Vapi, and Pipecat.

We’re excited to keep building alongside the best teams pushing voice AI forward and running Ink-2 in production. We’ve already pushed out a world class English model, and multilingual support is on the way, so Ink-2 fits the way your users speak, wherever they are.

Try Ink-2

Test Ink-2 out for yourself today

The quickest way to get started with Sonic is by using an integration. If you are using the API directly, check out Cartesia’s client libraries and AI tools.

The references section contains complete documentation for all API endpoints and best practices.

Prompting tips

Get natural-sounding output from Sonic with minimal prompt engineering.

Custom Pronunciations

Specify custom pronunciations for words that are hard to get right, like proper nouns or domain-specific terms.

Volume, Speed, and Emotion

Control the speed, volume, and emotion of generated speech.

SSML Tags

Laughter, pauses, and mid-transcript controls

Compare TTS Endpoints

How bytes, SSE, and WebSocket differ for text-to-speech, and when to use each.

Output Format

How to find the right parameters for output audio

Migrating from Sonic 3 to Sonic 3.5

What's new in Sonic 3.5 and what to know before you switch.

Voices

Instant Voice Clone

Learn how to get the best voice clones from your audio clips

Pro Voice Clone

Create near replica voices by leveraging more of your data

Multilingual Voices

Make a voice sound native in new languages and accents.

Streaming Transcripts

Contexts and Continuations

Generating audio from partial transcripts

Context Flushing and Flush IDs

Separating a continuation into multiple parts

Buffering

Control how text is buffered before speech generation to balance prosody and latency

Learn how to stream input text to Sonic TTS

In many real-time use cases, you don’t have input text available upfront—like when you’re generating it on the fly using a language model. For these cases, we support input streaming through a feature we call continuations.

This guide will cover how input streaming works from the perspective of the TTS model. If you just want to implement input streaming, see the WebSocket API reference, which implements continuations using contexts. The Python and TypeScript SDKs handle the continue flag for you: ctx.push() sends each chunk with continue: true, and ctx.no_more_inputs() sends continue: false. See the WebSocket continuations example for working code.

Continuations are generations that extend already generated speech. They’re called continuations because you’re continuing the generation from where the last one left off, maintaining the prosody of the previous generation.

If you don’t use continuations, you get sudden changes in prosody that create seams in the audio.

Prosody refers to the rhythm, intonation, and stress in speech. It’s what makes speech flow naturally and sound human-like.

Let’s say we’re using an LLM and it generates a transcript in three parts, with a one second delay between each part:

1. Hello, my name is Sonic.
2. It's very nice
3. to meet you.

To generate speech for the whole transcript, we might think to generate speech for each part independently and stitch the audios together:

Figure 1: Generate transcripts independently & stitch them together.

Unfortunately, we end up with speech that has sudden changes in prosody and strange pacing:

Now, let’s try the same transcripts, but using continuations. The setup looks like this:

Figure 2: Generate transcripts using continuations.

Here’s what we get:

As you can hear, this output sounds seamless and natural.

You can scale up continuations to any number of inputs. There is no limit.

Caveat: Streamed inputs should form a valid transcript when joined

This means that "Hello, world!" can be followed by " How are you?" (note the leading space) but not "How are you?", since when joined they form the invalid transcript "Hello, world!How are you?".

In practice, this means you should maintain spacing and punctuation in your streamed inputs.

End complete sentences with closing punctuation (for example ., ?, or !).

If a streamed chunk does not end with sentence-ending punctuation, the model often treats it as an incomplete sentence. That can cause:

• Extra latency: Text may stay in the automatic input buffer until the model sees a clearer boundary or until max_buffer_delay_ms elapses (3000ms by default), so audio starts later than you expect.
• Audio artifacts: The model expects natural sentence endings; without closing punctuation, the generated audio sometimes ends with odd or distorted sounds.

When a user-facing utterance is finished, put terminal punctuation on the final segment (and signal that no more text is coming on the context when appropriate, for example no_more_inputs() in the SDK or continue: false over the WebSocket).

Automatic buffering with max_buffer_delay_ms

When streaming inputs from LLMs word-by-word or token-by-token, we buffer text until the optimal transcript length for our model. The default buffer is 3000ms, if you wish to modify this you can use the max_buffer_delay_ms parameter, though we do not recommend making this change.

If you plan on using speed or volume SSML tags with buffering, make sure decimal values are not split up. Submitting 1.0 as 1, ., 0 will result in unintended failure modes.

How it works

When set, the model will buffer incoming text chunks until it’s confident it has enough context to generate high-quality speech, or the buffer delay elapses, whichever comes first.
Without this buffer, the model would immediately start generating with each input, which could result in choppy audio or unnatural prosody if inputs are very small (like single words or tokens).

Configuration

• Range: Values between 0-5000ms are supported
• Default: 3000ms

Use this only if

• you have custom buffering client side, in which case you can set this to 0
• you have choppiness even at 3000ms, in which case you can try a higher value

// Example WebSocket request with `max_buffer_delay_ms`
{
  "model_id": "sonic-3.5",
  "transcript": "Hello", // First word/token
  "voice": {
    "mode": "id",
    "id": "a0e99841-438c-4a64-b679-ae501e7d6091"
  },
  "context_id": "my-conversation-123",
  "continue": true,
  "max_buffer_delay_ms": 3000 // Buffer up to 3000ms
}

Let’s try the following transcripts with continuations and the default max_buffer_delay_ms=3000:

['Hello', 'my name', 'is Sonic.', "It's ", 'very ', 'nice ', 'to ', 'meet ', 'you.']

Turn detection controls

Adjust turn-start, turn-end, and eager-end thresholds to balance response speed against detection accuracy. See the Turn Detection guide for more details.

Professional Voice Clones now available on Sonic 3.5

They deliver better speaker similarity and more stable generation than on Sonic 3, especially for rare or non-native accents.

Test sample rates

Set any sample rate from 8 to 44.8 kHz based on your intended use case on the TTS Playground.

Upload knowledge bases

Let agents access domain-specific information via docs including FAQs, pricing, and guides. Set it up with the Knowledge Base guide.

Batch outbound calling

Send up to 5,000 calls with a single API request. Control how many run at once, track status, retry failed calls, and schedule batches for later. See the batch calling guide.

Zero data retention

Enable ZDR so transcripts, audio recordings, and logs from agent calls are never stored. Now available for Enterprise customers.

Call Redaction API

Delete the transcript, audio recordings, and logs for any call on demand. The call record itself is preserved with non-sensitive operational metadata. Available via the Delete Call API.

Smoother preview calls

Preview calls on the Playground now have lower latency and fewer dropped connections. Try calling one of your voice agents or a Cartesia voice in the voice library.

Your most-used voices, now multilingual

10 of our most popular voices, including Brooke and Blake, now support ~10 new languages with native-sounding accents, so you can serve global audiences with a consistent voice.

Better localization

Localized voices now have even more natural-sounding accents across supported languages with recent updates to the localization model.

Ink-2

our state-of-the-art streaming STT model — Build responsive real-time voice experiences with built-in turn detection and accurate transcription even in noisy environments. It currently supports only English, with additional languages coming later.

• Try it on the Cartesia Playground.
• Integrate via API, Python, TypeScript/JavaScript, LiveKit, and PipeCat.
• Switching from Deepgram Flux? See the migration guide.

Sonic 3.5 is now generally available

Our most natural, expressive TTS model is out of preview and production-ready. Use the sonic-3.5 alias for the latest stable snapshot. See the Sonic 3.5 model overview.

• Switching from Sonic 3? See Migrating from Sonic 3 to Sonic 3.5 for what’s new and what to check before moving production traffic.

Speed and volume controls

Dial speed and volume up or down so voices sound the way you want. See the speed and volume guide.

Line / Agents

• More natural conversations — Eligible Line agents run on Sonic 3.5 (TTS) and Ink 2 (STT) by default, improving naturalness, pacing, latency, and turn-taking. No config change needed.
• Bring your own Twilio account — Connect your Twilio account and import your existing phone numbers. You can still use the free Cartesia-provisioned numbers included in your plan. See the Twilio integration guide.
• SIP trunking (Beta) — Connect your existing phone system directly to Cartesia’s voice agents using SIP (Session Initiation Protocol) trunking. Reach out at [email protected] for early access.
• Phone number and provider APIs — Provision, import, and configure phone numbers and providers via API. See the phone numbers API.

Voices

• Filter voices by locale — Find voices with the right accent by passing a locale (e.g. en-GB) into the language field when listing voices. The API response now includes a country field (e.g. GB) to make each voice’s regional accent easier to identify. See the voices API reference.
• 57 new voices across 11 locales — Added 57 new voices in the voice library, including ar-AE, de-DE, en-CA, en-GB, en-NZ, en-US, en-ZA, es-MX, fr-CA, he-IL, and th-TH.

Sonic 3.5

Sonic 3.5 is now available on sonic-3-latest. We’d love for you to try it and tell us what you think.

Why you should try it

• More natural speech, pacing, and emotional expression, especially noticeable on expressive, conversational, and support-style transcripts.
• Cleaner audio quality across all languages and voices.
• Better alphanumeric read-out — confirmation codes, order numbers, phone numbers, IDs, and emails sound meaningfully more natural, in all supported languages.
• Step-change multilingual performance, particularly Hebrew, Japanese, Spanish, Hindi, German, Korean, and French.
• English heteronyms — tricky English heteronyms like “read,” “bass,” and “bow” now pronounce correctly in context.

How to try it

1. Point your API call or Playground request to the model ID sonic-3-latest.
2. Keep your existing voice IDs, request shape, and prompting — no code changes required for most customers.
3. Send us feedback on any voice or transcript that behaves differently than you expect.

As with any -latest alias, sonic-3-latest can be updated without notice and is not recommended for production. Pin to a dated snapshot (e.g. sonic-3) for production traffic.

What to know to be successful

• Spell tags still work the same way. If you already wrap alphanumerics in <spell>...</spell>, you don’t need to change anything — you’ll just get better-sounding output. See Prompting Tips for more details.
• If you use custom delimiters (commas/periods between characters or groups) to control pacing, our recommended format has changed. Use spaces between characters and commas between groups, e.g. A B C, 1 2 3 instead of A, B, C. 1, 2, 3. See Prompting Tips for more details.
• Speed and volume controls are temporarily disabled on sonic-3-latest. If you rely on speed or volume augmentation (including via SSML), stay on sonic-3 for now. We believe that Sonic 3.5 has more natural pacing and you may find that you don’t need to use speed control as much when using this model.
• Timestamps behave slightly differently. If you use end-of-word timestamps for interruption handling, you should not see a meaningful change. If you depend on beginning-of-word timestamps, please test carefully and reach out if you see regressions for your use case.
• Existing Professional Voice Clones (PVCs) do not carry over to sonic-3-latest. Professional Voice Clones are pinned to the base model they were trained on (e.g. sonic-3) and will function as a standard voice clone for this model. For more information, see Pro Voice Clone.
• Providing proper context to the model improves naturalness. Please see our buffering guide here for more details.

Where to look for help

• Sonic 3.5 model overview
• Prompting tips for Sonic 3.5
• Model aliases and snapshots

API

• Usage and API keys — New HTTP APIs for usage and API keys.
• Speech-to-text (STT) — Improved documentation. See STT streaming.

Playground

• Improved call details experience — Click on a transcript to seek audio when reviewing calls.
• Cancel call — You can now cancel active calls from the Playground, for example, if you mistakenly made outbound calls.
• Keys — One Keys screen with Standard and Admin tabs when your org has access.
• Pronunciation dictionaries — In-app list and detail views for dictionaries tied to your organization.

Line / Agents

• LLM provider — Agent inference paths standardize on Anthropic; setup copy and defaults no longer point voice agents at Gemini keys.
• OpenAI WebSocket mode — We now support OpenAI’s WebSocket mode, which offers low latency for agent inference.
• Transfer and end call interruption — In the Line SDK, you can set transfer and end call as uninterruptible.

Models / Voices

• Voice Library — 34 new voices across 10 locales (ar-001, de-DE, en-US, en-AU, he-IL, hi-IN, ko-KR, tl-PH, ta-IN, te-IN).
• Voice cloning — More reliable uploads for M4A (and similar) source clips when creating clones.

Self-hosted

• Playground — Add voices to your on-prem deployment.
• Pronunciation dictionaries — POST /onprem/add-pdict to import dictionaries from cloud into self-hosted stacks.
• STT — Optional streaming STT via your configured provider integration in self-hosted environments.

Breaking

• Text-to-Agent (T2A) API — Text-to-Agent workflow for Line is deprecated.

API

• Error responses — For Cartesia-Version: 2026-03-01, we now return structured JSON. See API Errors. API versions before 2026-03-01 continue to return legacy error formats (for example HTTP Title: Message).
• Voices — PATCH /voices/{id}: voice owners can now update accent and gender. Voice creation validates language. Invalid voice UUIDs and pronunciation-dictionary IDs return 404 instead of ambiguous errors.
• PVC model routing — PVC voices require a dated model ID (e.g. sonic-3-2026-01-12) instead of sonic-3. See Pro Voice Clone.
• Voice search — Name and metadata search is diacritics-insensitive.

Playground

• Pro voice clones
  • Clearer language mismatch messaging
  • Background noise removal is now a simple on/off control
  • Fine-tuning model support:
    • Removed support for older models
    • Now only sonic-3-2026-01-12 is supported
• Multilingual agents — Multilingual agent configuration is now supported in the Playground.
• Agents UI — Search by call ID and agent ID.

Billing

• Concurrency — Organizations can receive notifications when concurrency nears configured limits.

Model / voice

• Professional Voice Clones — Backend updates improve stability of the professional voice cloning workflow.
• Accents & filters — Additional accent options (e.g. Irish, New Zealand, South African, Belgian) and locale aliases for accent filtering in APIs and Playground.
• Voice Library — 94 new voices across 17 locales (including Arabic, German, English variants, Spanish, Finnish, French, Hebrew, Hindi, Japanese, Korean, Polish, Portuguese, Swedish, Telugu, Thai, and more).

Self-hosted

• On-premises — API for managing voices on self-hosted deployments.

Cartesia SDK

• cartesia-js v3.0.0 (Mar 2) — Major updates:
  • New features: flush_id included in chunk and voice changer binary responses; output_format and infill support; inline WebSocket response types; byte endpoint returns ArrayBuffer; improved WebPlayer and client export.
  • Fixes: memory leak and timing issues with abort signals/listeners, handling of empty Content-Length, and TimeoutError now includes a message.

See cartesia-js releases for full details.

Line

• History Management API: You can add or replace the history provided to your agent, for example, to summarize a long conversation.
• Custom User Events: You can send bidirectional custom events between your client and the agent. You could use this, for example, if you have a web application with UI interactions.
• Uninterruptible Messages: You can set messages as uninterruptible. A common use case is a legal disclaimer at the beginning of a call.
• End Tool Call Improvements: The default end call tool call is more conservative to prevent calls from ending prematurely.

API

• Increased reliability of API connections

Cartesia SDK

• cartesia-python v3.0.0 (Feb 9). See full details in cartesia-python releases.

Playground

• Shipped a new TTS page
• Shipped a new Voice Creation page
• Shipped a new Agents page

Model changes

• Improved pronunciation of real-world text patterns across languages
  • Enhanced support for structured and formatted speech patterns: numbers, dates, times, currency, phone numbers, IDs, percentages, and amounts/measurements.
  • Support for various date formats (YYYY-MM-DD, YYYY/MM/DD, 年月日).
  • Support for measurement units (meters, kg, tablespoon, gigabytes, etc.) with locale awareness.
  • Support for domestic and international phone number formats with locale-specific chunking for French, Italian, German, Portuguese, Korean, and more.
  • Improved alphanumeric ID handling with katakana/hiragana readings and Latin acronym transliteration to katakana for Japanese.
  • Improves all languages except English, Hindi & other Indic languages, Arabic, Hebrew, Chinese, Swedish, Georgian, Bulgarian, and Tagalog (targeted for future updates).
• Support for regional and locale-specific pronunciation within languages
  • Regional voices use region-specific terms in addition to accent (e.g. Belgian and Swiss French “nonante” vs. Canadian and French “quatre-vingt-dix”).
  • Region-specific number terminology, currency symbols, date formats, and measurement units.
  • Locale-aware date and time formatting (e.g. Russian year suffixes, French/Spanish time conventions).
  • Locale-aware currency symbol handling (e.g. $ as “dollars” in en_US and “pesos” in es_MX).
  • Locale pronunciation falls back to the primary country for that language (e.g. US for English, Brazil for Portuguese). We will continue to expand locale-aware support.
  • Improves all languages except English, Hindi & other Indic languages, Arabic, Hebrew, Chinese, Swedish, Georgian, Bulgarian, and Tagalog (targeted for future updates). Existing regional pronunciation for English voices (e.g. British) is unaffected.

Voice changes

• Voice Library: 39 new voices across 21 locales

Breaking changes effective June 1, 2026

The following model snapshots and languages are discontinued effective June 1, 2026:

• sonic: All snapshots and languages
• sonic-english: All languages
• sonic-multilingual: All languages
• sonic-2: snapshots sonic-2-2025-04-16, sonic-2-2025-05-08, sonic-2-2025-06-11; languages it, nl, pl, ru, sv, tr, hi
• sonic-2: snapshot sonic-2-2025-03-07; all languages
• sonic-turbo: snapshot sonic-turbo-2025-06-04; languages it, nl, pl, ru, sv, tr
• sonic-turbo: snapshot sonic-turbo-2025-03-07; all languages

The following endpoints are discontinued effective June 1, 2026:

• Voice Embedding: POST /voices/clone/clip (replacement: Clone Voice)
• Mix Voices: POST /voices/mix (no replacement)
• Create Voice: POST /voices (replacement: Clone Voice)

The following endpoints stop accepting voice embeddings effective June 1, 2026:

• TTS (bytes): POST /tts/bytes (replacement: Voice ID)
• TTS (SSE): POST /tts/sse (replacement: Voice ID)
• TTS (WebSocket): WSS /tts/websocket (replacement: Voice ID)

API

Regionalization — Calls routed to US, EU, APAC by origin.

Parameterized outbound calls — Docs

Pronunciation dictionaries — Docs

Model changes

• Sonic-3 model versioning scheme introduced
  • New preview track: sonic-3-latest (continuous updates for early access and feedback).
  • Stable track: sonic-3 always points to the most recent stable release.
  • Immutable dated snapshots: sonic-3-YYYY-MM-DD never change.
  • Details: Continuous updates and model snapshots
  • Promotion to stable checkpoint:
    • sonic-3-2026-01-12
      Included improvements: consistent speed & volume, custom IPA pronunciations with stronger adherence, Hindi prosody improvements, Korean prosody/intonation improvements.

Voice changes

• Featured Voices launched — Curated set of 30+ best-performing voices (e.g. Cathy, Henry).
• Voice Library — December: 25 new voices across 6 languages.
• Voice Library — January: 9 Spanish voices (Mexican, Colombian, Castilian).

Playground

• Voice library usability improvements (test with your own scripts, call an agent per voice).
• One-click Report Issue on TTS Playground.
• Mini voice picker (recently used + saved) on TTS page.
• PVC UI + reliability (loading skeletons, error messages, better behavior with large datasets and silence).

Line

• Line SDK v0.2 — Repo. Improved DX, long-running tool-call handling, committed turns, better turn-taking and transcription.

Reimagine your voice with our AI voice changer

Let our AI re-deliver your words in another voice, exactly the way you want them to sound.

TRY IT OUT

TALK TO SALES

TRUSTED BY 50K+ CUSTOMERS

Transform your voice today
Experience precise control over the speech you generate on our platform. Show us how you want something to be said, and our voices will deliver it perfectly, every time.

EXTENSIVE VOICE LIBRARY

Discover a diverse collection of unique voices in our voice library to bring your content to life.

CUSTOM VOICES

Mix multiple voices, customize speed and emotions to design your custom voice.

TRANSLATION AND LOCALIZATION

Our AI voice changer excels at localization, preserving the original voices and emotions.

Instantly change your voice from a 3 second clip Scale up to hours of content with Fine-Tuning

• SOURCE
• ORACLE
• BRIGHTON
• SOURCE
• HERO VOICE
• ROBOTIC MALE
• SOURCE
• PIPPA
• OVERLORD

"Cartesia’s Sonic model is a game-changer for our Conversational Video Interface. Its ultra-low latency of 90ms and high-quality voice generation have enabled us to create truly immersive real-time conversations with AI digital twins. The natural voices and voice design capabilities have elevated our product to new heights."
— Hassaan Raza, Co-Founder and CEO, Tavus

Make your content accessible to a global audience
Sonic supports seamless speech in 15 languages, with more added every release.

15 LANGUAGES

From Japanese to German—any language you need, we’ve got it.

LOCALIZATION

Localize a given voice to any accent or language.

• German
• English
• Spanish
• French
• Japanese
• Portuguese
• Chinese
• Italian

What our customers say
Join the growing list of companies opting for Sonic.

TRY IT NOW

TALK TO SALES

"Cartesia’s voice API power dynamic and empathetic conversational experiences that are consistently dependable. What really stands out to me is how natural and considerate the responses feel—especially the empathetic tone in statements like ‘I’m sorry, that must be frustrating.’"
Sami Ghoche, CEO of Forethought

"In 1999, Salesforce brought software to the cloud. In 2025, 11x is killing software as we know it and unleashing the era of digital workers. To realise this vision, we needed AI voice technology that feels truly human. Cartesia’s technology gives our AI digital workers reps the speed, reliability, and natural expressiveness required to engage customers at scale.
It's the only solution fit for our relentless drive toward innovation.”
Keith Fearon, Head of Product & Growth, 11x

"Before conversational voice models like Cartesia, Thoughtly relied on legacy text-to-speech APIs from major cloud providers. Nearly two years later, the evolution of this technology is staggering—customers can clone their voice and hear it speaking autonomously over the phone in just 60 seconds.”
Torrey Leonard, CEO, Thoughtly

Lifelike, expressive voices for every use case
Support
Power support experiences that delight your customers.

Gaming
Bring your storytelling to life with immersive voices

Content
Create content that engages viewers and drives clicks.

Media
Narrate content for podcasts, news, and publishing.

Healthcare
Empower healthcare with voices that patients trust.

Sales
Scale sales with lifelike voices that lead to conversions.

Voice Agents
Build responsive AI voice agents for any use case.

Dubbing
Go global with localized voices and accents for every language.

Avatars
Create expressive, relatable AI avatars for any use case.

Logistics
Automate complex logistics with voice-enabled systems.

Recruiting
Screen candidates with AI-powered voice interviews.

Accessibility
Make your content accessible to anyone, anywhere.

How to Use Our AI Voice Changer

STEP ONE

Try Cartesia's AI voice changer on our website. Simply create a free account and upload your original recording.

STEP TWO

Choose your preferred voice and language settings. Transform your voice with our lifelike voice changer.

STEP THREE

Apply voice changes to your content to hear it in a different voice, with complete control over the delivery.

Frequently asked questions

• How does the free AI voice changer work?
• What is a realtime voice changer client?
• Can I use the voice changer for gaming?
• Is the voice changer free to use?
• How do I access the voice changer?
• What makes our voice changer unique?

At Cartesia, our mission is to build technology that amplifies human potential and enriches everyday experiences. That vision only matters if it’s grounded in responsibility—so we design AI that earns trust and gives organizations full control.

Today, we’re excited to share a major milestone: our text-to-speech platform is now GDPR compliant. This achievement reflects months of rigorous work and reaffirms our unwavering commitment to data protection and privacy—whether we’re safeguarding personal documents, powering business communications, or bringing your creative content to life. It’s another big step toward making responsible, human-centered AI accessible to organizations everywhere.

GDPR compliance gives our customers confidence that we meet the EU’s strict standards for lawful data processing, uphold data subject rights, and enforce the robust security measures the regulation requires.

This milestone also builds on Cartesia’s strong security foundation—including SOC 2 Type II, PCI-DSS (service level provider), HIPAA, and optional Zero Data Retention—so personal data is protected to the highest standards across every layer of our platform.

At the heart of it all is our simple belief: privacy is one of the bedrocks of trust. By meeting GDPR’s rigorous requirements, we give every customer confidence that their data is handled with the highest level of respect and care.

Explore how we safeguard your data in our Privacy Policy and Data Processing Addendum.

Voice is harder than text

Every day, Sierra’s customers simulate tens of thousands of conversations with mock user personas to make sure their agents are ready for prime time. Voice Sims — a pioneering feature that tests voice agents in real world conditions before they talk to a single customer — is key to this process.

Voice poses very different challenges from text: the cadence of conversations matters enormously — when to stop and start talking, or pause; words can be easily misunderstood given accents, background noise, industry acronyms, and bad connections; and a flat tone or poor word choice can make even a correct answer land badly.

It’s these messy, human details that make voice so challenging, and yet so magical when it works. Dedicated voice testing ensures you end up with a fluent, natural sounding agent — not a stochastic parrot or talking chatbot.

Introducing Voice Sims

Voice Sims enable you to create multiple “users,” who speak different languages, have different needs, call from different locations (at home with the TV on, from the street, on a train), in different emotional states, and in different situations. Once generated, you can run them multiple times before, during, or after launch — and the results are then evaluated by another agent.

See Voice Sims in action.

Voice Sims run in parallel with other modalities : sharing the same evaluation infrastructure; plugging into Sierra’s Agent Studio and your CI/CD pipelines; and gating releases just like unit tests. Under the hood it’s a real, production grade voice conversation that tests every dimension of a call — not just the words on a page, but the way they are spoken, understood, and heard.

• Hear how your agent will perform in the real world. This includes: speech to text accuracy — the ability to transcribe what a consumer says accurately regardless of their language, accent, speaker set-up or background noise, as well as industry specific or technical terms; speech accuracy — the ability to read back license plates, account numbers or dates of birth correctly; and its overall behavior — pausing when interrupted, asking for missing context, phrasing responses appropriately, and generally keeping the conversation moving along.
• Measure your agent’s emotional intelligence. Not every caller is calm and patient. Some are confused, frustrated, or even angry. Voice Sims can create these emotional scenarios and reveal whether your agent responds appropriately — apologizing where needed, adopting a reassuring tone, going faster or slower, avoiding robotic phrasing that inflames an already heated situation. It’s not enough to get the facts right, calls have to feel empathetic and human too.
• Evaluate the entire voice stack end-to-end. Voice Sims pinpoint whether errors come from recognition (inaccurate transcription due to background noise or accents), reasoning (policy gaps or logic errors), or synthesis (an unnatural pitch, poor intonation or mispronunciations). Just as importantly, they measure latency and turn-taking — making sure your agent doesn’t pause too long, speak over the customer, or otherwise break the rhythm of a natural conversation.
• Assess whether your agent is sticking to your design rules and guardrails. For example, agents must authenticate users with spoken dates of birth or addresses instead of “magic links,” avoid reading out long URLs, and provide keypad fallbacks when needed. Voice Sims encode these rules as automatic checks, so every release respects them without relying on manual quality assurance testing.
• Measure performance across releases. Voice Sims enable you to view and aggregate key performance metrics like latency or error rates over time — making it easier to identify and avoid regressions as you upgrade your agent. On a per journey basis, you can diagnose and fix bugs before they reach production, and understand precise improvements release over release.

Easy, intuitive to use

Voice Sims sit alongside your chat simulations in Agent Studio, Sierra’s no code tool for building and managing agents. As you create new journeys or information your agent needs to handle, you can automatically simulate different modes of conversation (voice, chat, etc). This makes it easy to ensure your test suite is robust, inspect transcripts alongside audio recordings, scrub through playback, and jump directly to a point of failure — for example, if a caller spelled out an email address and the agent misheard the domain.

Why it matters

The impact of Voice Sims is simple but profound: agents become more reliable and more empathetic, and conversations more natural. By continuously creating simulated conversations, you catch brittle “only in calls” bugs early. By testing noisy, emotional, interrupted conversations on repeat, you refine prompts, and delivery until they sound right. And because it’s automated, teams can run fast — re-doing the same tough scenarios on every change, just like with unit tests, to ensure the agent is launch ready and improving over time.

For years, it was prohibitively expensive for most companies to talk to their customers. AI is changing all that, and adoption of voice is now skyrocketing. Sierra's platform will handle hundreds of millions of our customer's calls this year. Voice Sims help businesses put their agents where their customers are, on the phone, in the wild, confused or frustrated, with dogs barking and kids yelling — ensuring they can handle all that human complexity and emotion naturally, and with grace. It’s how we can create better, more human customer experiences with AI, while also driving better business outcomes for companies.

Over the past 12 months, tens of thousands of developers have built and productionized industry-leading voice agents using our frontier speech models, Sonic and Ink. In serving these developers, we found that even the most sophisticated teams struggled to build great voice agents with the tools available today.

Voice agents are uniquely hard to bring to production: they require maintaining natural, low-latency conversations with advanced reasoning across millions of calls. A few challenges come up repeatedly—more reasoning introduces higher latency, small changes to one component can cause unpredictable quality swings, and fragile infrastructure across multiple providers make scaling unpredictable.

That’s why we built Line. Line is the modern voice agent development platform, making it easy for developers and businesses everywhere to build best-in-class voice agents.

Line is code-first

The best products are built with code. We realized this early as we reflected on the challenges developers faced. Great businesses transform industries by putting code at the center – Stripe reimagined payments, Twilio transformed communications, and Vercel redefined web.

Intelligent agents and great conversations are impossible to express in rigid conversational builders, which put limits on reasoning ability. Instead, the best voice agents should be like the best humans, using fluid context, advanced logic, and background reasoning.

Line uses code to give you the flexibility to perfect every part of your voice agent. The Line SDK makes it intuitive to build advanced voice agents with background reasoning, and is designed to cover any use case. Edge cases are easy to handle directly in code, and you can integrate your favorite packages alongside our SDK, no compromises necessary.

With AI, code is the fastest way to build and more accessible than ever. Developers are writing more lines of code than ever, using AI to build complex applications quickly. Our code-first approach and SDK roadmap is designed with this future in mind.

Line helps you iterate fast

Building great voice agents is an iterative process. Progress comes from making changes, testing them in live conversations, learning what works, and adjusting based on feedback. Line helps you move through that cycle quickly.

Line gets you to your first agent in minutes, starting from a text prompt or template. With our CLI and GitHub integrations, you can develop agents locally, deploy with one command to our platform, and talk to your agents in seconds. You can even share your agent with others.

Every iteration requires comprehensive evals and manual testing to get right. Developers constantly refine prompts, business logic, and background reasoning. They need to measure progress on their agents over time.

Line records all calls to deployed agents, saves the audio and transcripts, reports system metrics like latency, and provides comprehensive logs for auditing and debugging. Developers can use custom LLM-as-a-judge metrics to rate calls along any axis, including user satisfaction and call success.

Line brings you our frontier models and infrastructure

Best-in-class voice agents require frontier speech models. At Cartesia, our research team is pioneering the world’s best speech models using breakthrough advances in AI architectures.

Sonic is the world’s lowest latency text-to-speech model, with ultra-realistic conversational voices, and reliable transcript following. Ink is the fastest streaming speech-to-text model for speech understanding. Collectively, Sonic and Ink have powered millions of calls for businesses, from the fastest growing companies in voice AI to the Fortune 500.

Deeply integrating models and infrastructure creates new opportunities to optimize the end-to-end voice agent experience. Line voice agents are deployed alongside our Sonic and Ink models for the fastest latencies, and they’ll be the first to access our latest research advances in speech modeling.

For enterprises, this integration extends further: Line can be deployed entirely on-prem, from voice agents to models, and models can be customized with fine-tuning.

Line, Sonic, and Ink run on Cartesia’s reliable, globally distributed infrastructure, allowing every deployed voice agent to scale to thousands of calls while maintaining low latency.

Line is now available

Line is available today to all developers. As part of our launch, all subscription tiers will get their equivalent monthly plan dollars prepaid towards agents—at no extra cost.

Our north-star is simple. No matter how complex the code you write, when you deploy to the Line platform, every call should be a flawless experience.

With Line, we hope to make frontier voice AI accessible to everyone, and in turn, to make AI more accessible to the world.

We’re excited to see what you build. Sign up and check out the docs now to create your first voice agent. Contact us to start enterprise plan discussions.