GET

/v1/schemas/fal/audio/fal-ai%2Fqwen-3-tts%2Fclone-voice%2F1.7b

Accept:

kind inputactivity audiohash 3e3a3883…extracted Jul 18, 2026version currentsource upstream spec ↗

Request body

2 properties · 1 required · 0 $defs

property	type	description	constraints
audio_url*	string	URL to the reference audio file used for voice cloning. Must be at most 300 seconds (5 minutes) long; a short clip of clean speech is sufficient.
reference_text	string	Optional reference text that was used when creating the speaker embedding. Providing this can improve synthesis quality when using a cloned voice.	nullable

Validate a payload

before you spend tokens

shell

$ curl -X POST https://modelschemas.com/v1/validate \
    -d '{"provider":"fal","endpointId":"fal-ai/qwen-3-tts/clone-voice/1.7b","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}