GET

/v1/schemas/fal/audio/fal-ai%2Fminimax%2Fvoice-clone

kind inputactivity audiohash b617014cextracted Jul 6, 2026version currentsource upstream spec ↗

Request body

6 properties · 1 required · 0 $defs
propertytypedescriptionconstraints
audio_url*stringURL of the input audio file for voice cloning. Should be at least 10 seconds long. To retain the voice permanently, use it with a TTS (text-to-speech) endpoint at least once within 7 days. Otherwise, it will be automatically deleted.
noise_reductionbooleanEnable noise reduction for the cloned voicedefault: false
modelenumTTS model to use for preview. Options: speech-02-hd, speech-02-turbo, speech-01-hd, speech-01-turbospeech-02-hd | speech-02-turbo | speech-01-hd | speech-01-turbo · default: "speech-02-hd"
textstringText to generate a TTS preview with the cloned voice (optional)length ≤ 1000 · nullable
need_volume_normalizationbooleanEnable volume normalization for the cloned voicedefault: false
accuracynumberText validation accuracy threshold (0-1)0 ≤ n ≤ 1 · nullable

Validate a payload

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