fal.ai·Speech to text

Queue OpenAPI for fal-ai/whisper

/fal-ai/whisperasync$0.003 / compute second

The OpenAPI schema for the fal-ai/whisper queue. Returns hosted file URLs (download promptly; fal keeps them for a limited time). Billed per compute second.

Charged per compute second produced; a call that produces nothing is charged one unit.

Input

languageany
Language of the audio file. If set to null, the language will be automatically detected. Defaults to null. If translate is selected as the task, the audio will be translated to English, regardless of the language selected.
promptstring
Prompt to use for generation. Defaults to an empty string. (default "")
taskstring
Task to perform on the audio file. Either transcribe or translate. (default "transcribe")
transcribe, translate
batch_sizeinteger
batch_size (default 64)
chunk_levelstring
Level of the chunks to return. Either none, segment or word. `none` would imply that all of the audio will be transcribed without the timestamp tokens, we suggest to switch to `none` if you are not satisfied with the transcription quality, since it will usually improve the quality of the results. Sw (default "segment")
none, segment, word
audio_urlstringrequired
URL of the audio file to transcribe. Supported formats: mp3, mp4, mpeg, mpga, m4a, wav or webm.
num_speakersany
Number of speakers in the audio file. Defaults to null. If not provided, the number of speakers will be automatically detected.
diarizeboolean
Whether to diarize the audio file. Defaults to false. Setting to true will add costs proportional to diarization inference time. (default false)

Field	Type	Required	Description
language	any	—	Language of the audio file. If set to null, the language will be automatically detected. Defaults to null. If translate is selected as the task, the audio will be translated to English, regardless of the language selected.
prompt	string	—	Prompt to use for generation. Defaults to an empty string. (default "")
task	string (transcribe, translate)	—	Task to perform on the audio file. Either transcribe or translate. (default "transcribe")
batch_size	integer	—	batch_size (default 64)
chunk_level	string (none, segment, word)	—	Level of the chunks to return. Either none, segment or word. `none` would imply that all of the audio will be transcribed without the timestamp tokens, we suggest to switch to `none` if you are not satisfied with the transcription quality, since it will usually improve the quality of the results. Sw (default "segment")
audio_url	string	yes	URL of the audio file to transcribe. Supported formats: mp3, mp4, mpeg, mpga, m4a, wav or webm.
num_speakers	any	—	Number of speakers in the audio file. Defaults to null. If not provided, the number of speakers will be automatically detected.
diarize	boolean	—	Whether to diarize the audio file. Defaults to false. Setting to true will add costs proportional to diarization inference time. (default false)

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/whisper","input":{}}'

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