API docs / Audio models

ElevenLabs v4 (v4 Turbo text to speech) API

Faster, half-price v4 speech for drafts and high-volume reads.

Model id
elevenlabs/tts/eleven-v4-turbo
Provider
ElevenLabs
Output
Audio
Price
From 1 credits per run, the same as on voor.ai. Options such as length or resolution can change it.

Request

POST https://voor.ai/v1/generations with "model": "elevenlabs/tts/eleven-v4-turbo". Poll GET /v1/tasks/{id} or receive the signed webhook. See the overview for keys, idempotency, webhooks and errors.

curl https://voor.ai/v1/generations \
  -H "Authorization: Bearer $VOOR_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
  "model": "elevenlabs/tts/eleven-v4-turbo",
  "input": {
    "prompt": "A red fox standing in fresh snow at golden hour, soft light"
  },
  "callback_url": "https://example.com/webhooks/voor"
}'

# Then poll the task (or wait for the webhook):
curl https://voor.ai/v1/tasks/TASK_ID \
  -H "Authorization: Bearer $VOOR_API_KEY"

Input parameters

NameTypeDetails
promptrequiredstring

The text to convert to speech, up to 5,000 characters. Supports audio tags such as [whispering] or [excited] and IPA pronunciation enclosed in forward slashes, for example /ˈiːfə/.

Up to 5000 characters

languagestring

Optional ISO 639-1 language code such as en, es or ja. Leave empty to detect the language from the text.

voicestring

The voice to use for speech generation.

Default: Rachel

One of: Rachel, Aria, Roger, Sarah, Laura, Charlie, George, Callum, River, Liam, Charlotte, Alice, Matilda, Will, Jessica, Eric, Chris, Brian, Daniel, Lily, Bill

seednumber

Seed for best-effort reproducibility. Identical output is not guaranteed.

Min 0 · Max 4294967295

apply_text_normalizationstring

Whether to spell out numbers, dates and prices before generation.

Default: auto

One of: auto, on, off

similarity_boostnumber

How closely the output follows the selected voice. Higher values increase similarity but may reduce naturalness.

Default: 0.75

Min 0 · Max 1

stabilitynumber

Voice stability. Lower values allow more expressive delivery; higher values make delivery more consistent.

Default: 0.5

Min 0 · Max 1