Skip to content
OM RouterOM Router Docs

Audio

OM Router supports text to speech, audio transcription, and audio translation. Enter the name of the corresponding audio model in each request.

Text to speech

Section titled “Text to speech”
POST /v1/audio/speech
Authorization: Bearer OMROUTER_API_KEY
Content-Type: application/json
Terminal window
curl --silent --show-error \
  'https://api.omrouter.com/v1/audio/speech' \
  --header "Authorization: Bearer $OMROUTER_API_KEY" \
  --header 'Content-Type: application/json' \
  --data "{
    \"model\": \"$OMROUTER_MODEL_ID\",
    \"input\": \"Hello from OM Router.\",
    \"voice\": \"model-supported-voice\"
  }" \
  --output speech.bin

Common optional fields include response_format, speed, and instructions. Use only values documented for the selected model.

Transcription

Section titled “Transcription”
POST /v1/audio/transcriptions
Authorization: Bearer OMROUTER_API_KEY
Content-Type: multipart/form-data
Terminal window
curl --silent --show-error \
  'https://api.omrouter.com/v1/audio/transcriptions' \
  --header "Authorization: Bearer $OMROUTER_API_KEY" \
  --form "model=$OMROUTER_MODEL_ID" \
  --form 'file=@audio.mp3'

Audio translation uses POST /v1/audio/translations with the same upload format. Supported file types and sizes depend on the selected model.