GET

/v1/schemas/fal/audio/fal-ai%2Fwizper

kind inputactivity audiohash d6e284c0extracted Jul 6, 2026version currentsource upstream spec ↗

Request body

7 properties · 1 required · 0 $defs
propertytypedescriptionconstraints
audio_url*stringURL of the audio file to transcribe. Supported formats: mp3, mp4, mpeg, mpga, m4a, wav or webm.
merge_chunksbooleanWhether to merge consecutive chunks. When enabled, chunks are merged if their combined duration does not exceed max_segment_len.default: true
languageenum Language of the audio file. If translate is selected as the task, the audio will be translated to English, regardless of the language selected. If `None` is passed, the language will be automatically detected. This will also increase the inference time. af | am | ar | as | az | ba · +93 more · nullable
max_segment_lenintegerMaximum speech segment duration in seconds before splitting.10 ≤ n ≤ 29 · default: 29
taskenumTask to perform on the audio file. Either transcribe or translate.transcribe | translate · default: "transcribe"
chunk_levelconstLevel of the chunks to return."segment" · default: "segment"
versionconstVersion of the model to use. All of the models are the Whisper large variant."3" · default: "3"

Validate a payload

before you spend tokens
shell
$ curl -X POST https://modelschemas.com/v1/validate \
    -d '{"provider":"fal","endpointId":"fal-ai/wizper","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}