API docs / Audio models

flash-v2.5 API

Converts text to speech using ElevenLabs's fastest speech synthesis model with ultra-low latency of approximately 75ms. Supports 32 languages including 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, Ukrainian, Hungarian, Norwegian, and Vietnamese. Features 26 predefined voices 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. Offers adjustable parameters for speech speed, voice stability, similarity boost, and style exaggeration. Supports up to 40,000 characters per request and includes context awareness through previous and next text inputs. Optimized for real-time applications, voice agents, chatbots, interactive applications, and large-scale text-to-speech processing.

Model id
elevenlabs/flash-v2.5
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/flash-v2.5". 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/flash-v2.5",
  "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