Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.routing.run/llms.txt

Use this file to discover all available pages before exploring further.

Use the audio endpoints for text-to-speech (TTS) and speech-to-text (STT). Both endpoints require an API key in X-API-Key or Authorization: Bearer.

​
Text-to-speech

POST /v1/audio/speech

​
Models

Model
route/eleven-v3
route/eleven-multilingual-v2
route/eleven-flash-v2.5
route/eleven-flash-v2

​
Request

curl -sS -X POST https://api.routing.run/v1/audio/speech \
  -H "X-API-Key: ${ROUTING_RUN_API_KEY}" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "route/eleven-flash-v2.5",
    "input": "Hello world, this is a test.",
    "voice": "JBFqnCBsd6RMkjVDRZzb"
  }' \
  --output output.mp3
The response is an audio file. mp3 is the default format.

​
Request body

​
Available voices

Voice IDDescription
JBFqnCBsd6RMkjVDRZzbDefault voice
EXAVITQu4vr4xnSDxMaLAnother available voice

​
Speech-to-text

POST /v1/audio/transcriptions

​
Models

Model
route/scribe-v2
route/scribe-v2-realtime
route/scribe-v1
route/whisper-large-v3
route/scribe-v2-realtime is for real-time streaming use cases only. Do not use it for batch transcription.

​
Request

curl -sS -X POST https://api.routing.run/v1/audio/transcriptions \
  -H "X-API-Key: ${ROUTING_RUN_API_KEY}" \
  -F "file=@audio.mp3" \
  -F "model=route/scribe-v2" \
  -F "language=en"

​
Form fields

​
Response

{
  "text": "Transcribed text here",
  "segments": [],
  "language": "en"
}
TTS and STT models are available on Premium, Max, and Ultra plans. Each audio request consumes 5 requests from your daily quota.