fal.ai·Speech to text

ElevenLabs Speech to Text

/fal-ai/elevenlabs/speech-to-textasync$0.06 / minute of audio

Generate text from speech using ElevenLabs advanced speech-to-text model. Returns hosted file URLs (download promptly; fal keeps them for a limited time). Billed per minute of audio.

Charged per minute of audio produced; a call that produces nothing is charged one unit.

Input

language_codeany
Language code of the audio
tag_audio_eventsboolean
Tag audio events like laughter, applause, etc. (default true)
audio_urlstringrequired
URL of the audio file to transcribe
diarizeboolean
Whether to annotate who is speaking (default true)

Field	Type	Required	Description
language_code	any	—	Language code of the audio
tag_audio_events	boolean	—	Tag audio events like laughter, applause, etc. (default true)
audio_url	string	yes	URL of the audio file to transcribe
diarize	boolean	—	Whether to annotate who is speaking (default true)

Run it

curl -s https://sooma.dev/v1/run \ -H "Authorization: Bearer $SOOMA_API_KEY" \ -H "Content-Type: application/json" \ -d '{"provider":"fal","endpoint":"/fal-ai/elevenlabs/speech-to-text","input":{}}'

Or ask your agent: it will call inspect for this schema and run it over MCP.