API docs / Audio models

v2-multilingual API

Generates multilingual text-to-speech audio in 29 languages with high emotional range and natural expressiveness. Features consistent voice quality across all supported languages while maintaining each speaker's unique characteristics. Offers 26 voice options including Rachel, Drew, Clyde, Paul, Aria, Domi, Dave, Roger, Fin, Sarah, James, Jane, Juniper, Arabella, Hope, Bradford, Reginald, Gaming, Austin, Kuon, Blondie, Priyanka, Alexandra, Monika, Mark, and Grimblewood. Supports up to 10,000 characters per request with stable long-form output quality. Languages include English, Japanese, Mandarin Chinese, German, Hindi, French, Korean, Portuguese, Italian, Spanish, Indonesian, Dutch, Turkish, Filipino, Russian, Polish, Swedish, Bulgarian, Romanian, Arabic, Czech, Greek, Finnish, Croatian, Malay, Slovak, Danish, Tamil, and Ukrainian. Provides configurable stability, similarity boost, style exaggeration, and speech speed controls with contextual awareness through previous and next text inputs.

Model id
elevenlabs/v2-multilingual
Provider
elevenlabs
Output
Audio
Price
From 2 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/v2-multilingual". 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/v2-multilingual",
  "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

stylenumber

Style exaggeration (0.0 to 1.0)

Default: 0

Min 0 · Max 1

languagestring

Language code (e.g., 'en', 'es', 'fr')

Default: en

voicestring

Default: Rachel

One of: Rachel, Drew, Clyde, Paul, Aria, Domi, Dave, Roger, Fin, Sarah, James, Jane, Juniper, Arabella, Hope, Bradford, Reginald, Gaming, Austin, Kuon, Blondie, Priyanka, Alexandra, Monika, Mark, Grimblewood

next_textstring

Next text for context

Default:

previous_textstring

Previous text for context

Default:

similarity_boostnumber

Similarity boost setting (0.0 to 1.0)

Default: 0.75

Min 0 · Max 1

speednumber

Speed of speech (0.25 to 4.0)

Default: 1

Min 0.7 · Max 1.2

stabilitynumber

Stability setting for voice generation (0.0 to 1.0)

Default: 0.5

Min 0 · Max 1