MuseSpan
ElevenLabs

elevenlabs/eleven-v3

Text to Speech

ElevenLabs' expressive v3 text-to-speech model. Inline audio tags such as [excited] or [whispers] give fine control over emotion and delivery across 70+ languages. Up to 5,000 characters per request.

Try itGet API keyOpenAPIllms.txt

93 / 5,000

93 characters · reserves $0.0093

More settings (4)
ResultExampleSign in to try

$0.10 / 1K characters · billed by the characters of your text

0:00 / 0:00
Download audio
Example — generated from this input

Hello! This is a test of the text to speech system, powered by ElevenLabs. How does it sound?

Pricing

Unit price $0.10 / 1K characters

Charged per 1,000 characters of input text, prorated to the exact length (spaces, punctuation and tags count).

Each request temporarily reserves the price of its own text ($0.10 per 1,000 characters, counted as Unicode characters and at least 1; at most $0.50 for the longest text; a request with an undeclared field, or other free text over 64 characters, reserves $0.50); you are charged for actual usage, usually within a minute: any unused amount is released and any usage above it is charged to your balance, even if that takes it below zero; while your balance is below zero, new requests are paused until a top-up covers it.

For example, 100 characters reserve $0.01; 1,000 characters reserve $0.10.

Your balance must be at least $0.01 and cover this reserve.

Failed generations are not charged.

API

Submit generation requests with this model ID.

POST/v1/model-tasks
elevenlabs/eleven-v3
Request body
{
  "model": "elevenlabs/eleven-v3",
  "input": {
    "apply_text_normalization": "auto",
    "stability": 0.5,
    "text": "Hello! This is a test of the text to speech system, powered by ElevenLabs. How does it sound?",
    "timestamps": false,
    "voice": "Rachel"
  }
}

Input schema

ParameterTypeRequirementDefault
textstringRequired—
apply_text_normalizationstringOptionalauto
language_codestringOptional—
stabilitynumberOptional0.5
timestampsbooleanOptionalfalse
voicestringOptionalRachel

Response

The API returns a result or a pollable asynchronous task. See the examples and Schema below for the response mode and result fields.

Asynchronous task
Submit response
HTTP 202
/v1/model-tasksapplication/json
{
  "id": "task_example",
  "model": "elevenlabs/eleven-v3",
  "status": "queued"
}
Status response
HTTP 200
/v1/model-tasks/{id}application/json
{
  "id": "task_example",
  "model": "elevenlabs/eleven-v3",
  "status": "completed",
  "output": {
    "audio": {
      "url": "https://api.musespan.com/v1/model-tasks/task_example/artifacts/0"
    }
  }
}
File download
HTTP 200
/v1/model-tasks/{id}/artifacts/{index}Generated audio (e.g. audio/mpeg)

When the task completes, file URLs in output point to this endpoint, numbered from 0. Send the same API key (Authorization header) when downloading.

Error response
HTTP 400
/v1/model-tasksapplication/json
{
  "error": {
    "code": "invalid_input",
    "message": "The input does not match this model's input schema. Check the model's API documentation.",
    "type": "invalid_request_error"
  }
}

Code examples

Async submission returns a task ID. Poll until status is completed, then retrieve the generated content from the result. Get your API key in the console.

# Use a new directory for each new generation. Rerunning here continues this task.
set -eu
test -s model-task-id.txt || python3 -c "import uuid; print(uuid.uuid4())" > model-task-id.txt
REQUEST_ID=$(cat model-task-id.txt)
# Idempotent: resending the same bytes with the same ID never charges twice.
curl --fail-with-body --retry 3 --retry-connrefused --request POST 'https://api.musespan.com/v1/model-tasks' \
  --header "Authorization: Bearer $MUSESPAN_API_KEY" \
  --header "X-Request-Id: $REQUEST_ID" \
  --header "Content-Type: application/json" \
  --data '{"model":"elevenlabs/eleven-v3","input":{"apply_text_normalization":"auto","stability":0.5,"text":"Hello! This is a test of the text to speech system, powered by ElevenLabs. How does it sound?","timestamps":false,"voice":"Rachel"}}'
# Poll every 5 seconds for up to 25 minutes until status is completed or failed.
# Still queued (with queue_position) 5 minutes after submission: failed with queue_timeout, not charged.
# No result 15 minutes after acceptance (or no confirmation 15 minutes after submission): failed with generation_timeout, not charged.
# Any failure is final: generate again in a new directory (a new X-Request-Id).
# A 404 means the POST did not arrive: rerun this script to resend it with the same ID.
curl --fail-with-body 'https://api.musespan.com/v1/model-tasks/'"$REQUEST_ID"'' --header "Authorization: Bearer $MUSESPAN_API_KEY"