GET

/v1/schemas/fal/audio/fal-ai/f5-tts

Accept:

kind inputactivity audiohash 5817c707…extracted Nov 6, 2026version currentsource upstream spec ↗

field	recorded source
schema	Source linked above. upstream-spec Source trace `d977a3519439fa780a8124a959f8bd47028b123cbb429fca1e62ce9e389b57a3` { "fetchedAt": 1793941202, "extractorVersion": "1", "verifiedAt": null }

Request body

6 properties · 3 required · 0 $defs

property	type	description	constraints
model_type*	enum	The name of the model to be used for TTS.	F5-TTS \| E2-TTS
ref_audio_url*	string	The URL of the reference audio file.
gen_text*	string	The text to be converted to speech. Maximum 5000 characters.
ref_text	string	The reference text to be used for TTS. If not provided, an ASR (Automatic Speech Recognition) model will be used to generate the reference text.	default: ""
remove_silence	boolean	Whether to remove the silence from the audio file.	default: true
enable_safety_checker	boolean	Check input content for safety. Disabling requires account authorization.	default: true

Validate a payload

before you spend tokens

shell

$ curl -X POST https://modelschemas.com/v1/validate \
    -d '{"provider":"fal","endpointId":"fal-ai/f5-tts","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}