Audio

ElevenLabs V3 TTS audio

ElevenLabs V3 text-to-speech — narração multilíngue de alta fidelidade com 21 vozes.

Category: Text-to-speech · elevenlabs-v3-tts

How to use & limits

Multilingual high-fidelity text-to-speech (TTS) with 21 voices.
text: 1 to 5,000 characters.
stability 0 to 1 (default 0.5) controls voice consistency.
Optional ISO 639-1 language_code enforces a language; optional timestamps returns a separate JSON file.

Capabilities

What this model supports, straight from the schema — no pricing, no infrastructure detail.

Capability	Value
`tts` Text-to-speech	Yes
`voice` Voice selection	Yes
`voices` Available voices	21
`max_prompt_length` Max prompt length	5000

Parameters

Fields accepted in params (or first-class, where applicable) for POST /generations.

Name	Label	Type	Required	Default	Options	Min / Max	Description
`timestamps`	Timestamps	boolean	Optional	false	—	—	When on, returns per-word timestamps in a separate JSON file.
`stability`	Estabilidade	number	Optional	0.5	—	0 – 1	Voice stability from 0 to 1; default 0.5.
`language_code`	Idioma (ISO 639-1)	text	Optional	—	—	—	Optional ISO 639-1 language code to enforce the language.
`apply_text_normalization`	Normalização de texto	select	Optional	auto	auto · on · off	—	Text normalization: auto (default), on or off.
`voice`	Voz	select	Optional	Rachel	Aria · Roger · Sarah · Laura · Charlie · George · Callum · River · Liam · Charlotte · Alice · Matilda · Will · Jessica · Eric · Chris · Brian · Daniel · Lily · Bill · Rachel	—	Narration voice (one of 21); default Rachel.
`text`	Texto	textarea	Required	—	—	—	Text to convert to speech, 1 to 5,000 characters.

Example request

bash

curl -X POST https://caranguejo.art/api/v1/dev/generations \
  -H "Authorization: Bearer $CK" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "elevenlabs-v3-tts",
  "text": "Hello! This is a test of the text-to-speech system.",
  "params": {
    "voice": "Rachel",
    "stability": 0.5,
    "apply_text_normalization": "auto",
    "language_code": "en",
    "timestamps": false
  }
}'

javascript

const res = await fetch("https://caranguejo.art/api/v1/dev/generations", {
  method: "POST",
  headers: {
    "Authorization": "Bearer " + process.env.CK,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "model": "elevenlabs-v3-tts",
    "text": "Hello! This is a test of the text-to-speech system.",
    "params": {
      "voice": "Rachel",
      "stability": 0.5,
      "apply_text_normalization": "auto",
      "language_code": "en",
      "timestamps": false
    }
  }),
});
const { data } = await res.json();

Example response

json

{
  "id": "9f0c1a7e-…",
  "object": "generation",
  "model": "elevenlabs-v3-tts",
  "type": "audio",
  "status": "completed",
  "output": {
    "assets": [
      {
        "url": "https://media.caranguejo.art/outputs/example.mp3",
        "type": "audio"
      }
    ]
  }
}

The job's real cost is returned as credits_charged on the completed response — check GET /balance for the account balance.

Common errors for this job type:

`insufficient_credits`	Account balance can't cover the job cost.
`content_policy_violation`	Prompt or media rejected by content policy.
`generation_timeout`	The job exceeded the maximum processing time.
`rate_limited`	Too many requests per minute.
`invalid_input`	A required parameter is missing or outside the model's schema.
`generation_failed`	Generic processing failure.