Eleven v3
ElevenLabs Eleven v3 — the most expressive TTS model, 70+ languages with audio tags.
ElevenLabs' most expressive model — 70+ languages with inline audio-tag control. Best for short, performance-heavy content (ads, characters, trailers) where emotional range matters more than length.
| Endpoint | POST /api/v1/tts/synthesize |
Model ID (ttsModel) | eleven-v3 |
| Provider | ElevenLabs (paid access) |
| Character Limit | 5,000 |
| Cost | 2,100 / 1K chars |
Shared conventions
Auth, the voice→provider rule, rate limits, and the full error table are on the Speech API page. This page covers only what's specific to Eleven v3.
How Eleven v3 expression works
v3 controls delivery through inline audio tags in your text — [laughs], [whispers], [excited], [sighs] — combined with stability. It has no speed or style sliders: the speed and style_exaggeration fields are ignored by v3 (those belong to Multilingual v2 / Flash). Use tags for emotion.
Match the voice's supported models
Only a small curated set of voices is eleven_v3-optimized (see a voice's
metadata.supported_models from GET
/api/v1/tts/voices). v3 still renders on
any voice, but forcing it on a voice tuned for v2/Flash — especially
Professional Voice Clones — lowers similarity. For those, prefer Multilingual
v2.
Request
Body
| Parameter | Type | Required | Description |
|---|---|---|---|
text | string | Yes | Text to synthesize (max 5,000 chars). Supports inline [audio tags]. |
voice | string | Yes | An ElevenLabs voice ID from GET /api/v1/tts/voices |
ttsModel | string | Yes | Must be "eleven-v3" |
stability | number | No | Voice stability 0.0–1.0 · Default: 0.5 |
similarity_boost | number | No | Similarity to source voice 0.0–1.0 · Default: 0.75 |
speaker_boost | boolean | No | Enhance speaker clarity · Default: true |
language_override | boolean | No | Force the voice's native language · Default: false |
response_format | string | No | "mp3_44100_128" "pcm_8000" "pcm_16000" "pcm_22050" "pcm_24000" · Default: "mp3_44100_128" |
title | string | No | Title for the saved project |
{
"text": "[excited] Welcome to Sonna! [whispers] Your audio is ready.",
"voice": "db4e815d-00aa-43e6-99cf-0d9b4db9a07a",
"ttsModel": "eleven-v3",
"stability": 0.5,
"similarity_boost": 0.75
}Response (200 OK)
{
"url": "https://cdn.sonnalabs.app/sonna/api-ephemeral/tts/paid/user123/abc123.mp3",
"remainingCredits": 99580,
"projectCreated": true
}Errors (400 TEXT_TOO_LONG over 5,000 chars, 403 PAID_ACCESS_REQUIRED, 409, 429, 503) follow the shared Speech API table.