Skip to main content

Basic request

curl https://beta.api.voiceos.com/v1/audio/transcriptions \
  -H "Authorization: Bearer vos_..." \
  -F "file=@sample.mp3" \
  -F 'messages=[{"role":"system","content":"You are helping inside a TypeScript codebase."},{"role":"user","content":"The file is SessionStreamService.ts and the env var is VOICEOS_TEAM_API_KEY."}]' \
  -F 'languages="en"' \
  -F 'response_format=json'

Audio-only (no messages)

curl https://beta.api.voiceos.com/v1/audio/transcriptions \
  -H "Authorization: Bearer vos_..." \
  -F "file=@sample.mp3" \
  -F 'response_format=json'

With multiple languages

curl https://beta.api.voiceos.com/v1/audio/transcriptions \
  -H "Authorization: Bearer vos_..." \
  -F "file=@sample.webm" \
  -F 'messages=[{"role":"user","content":"The user may mention LangGraph, QdrantVectorCache, and RAGPipelineConfig."}]' \
  -F 'languages=["en","ja"]' \
  -F 'dictionary=["VoiceOS","ASR"]' \
  -F 'response_format=json'

Save response

curl https://beta.api.voiceos.com/v1/audio/transcriptions \
  -H "Authorization: Bearer vos_..." \
  -F "file=@sample.mp3" \
  -F 'messages=[{"role":"user","content":"Use observabilityTags, providerFallback, and asrRoutingDecision as context."}]' \
  -F 'languages="auto"' \
  -F 'response_format=json' \
  -o transcription.json