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
| Name | Type | Details |
|---|---|---|
promptrequired | string | The text to convert to speech |
style | number | Style exaggeration (0.0 to 1.0) Default: Min 0 · Max 1 |
language | string | Language code (e.g., 'en', 'es', 'fr') Default: |
voice | string | Default: 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_text | string | Next text for context Default: |
previous_text | string | Previous text for context Default: |
similarity_boost | number | Similarity boost setting (0.0 to 1.0) Default: Min 0 · Max 1 |
speed | number | Speed of speech (0.25 to 4.0) Default: Min 0.7 · Max 1.2 |
stability | number | Stability setting for voice generation (0.0 to 1.0) Default: Min 0 · Max 1 |