GET

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

Accept:

kind inputactivity audiohash d7b19fed…extracted Oct 9, 2026version currentsource upstream spec ↗

field	recorded source
schema	Source linked above. upstream-spec Source trace `2205cf1a16bc380b23fa796f3490f3d4bf07a9baaef6b624382b317e75449e33` { "fetchedAt": 1791522002, "extractorVersion": "1", "verifiedAt": null }

Request body

5 properties · 1 required · 0 $defs

property	type	description	constraints
text*	string	The text to be converted to speech. You can additionally add the following emotive tags: <laugh>, <chuckle>, <sigh>, <cough>, <sniffle>, <groan>, <yawn>, <gasp>
enable_safety_checker	boolean	Authorized callers may set false to request relaxed screening.	default: true
voice	enum	Voice ID for the desired voice.	tara \| leah \| jess \| leo \| dan \| mia · +2 more · default: "tara"
temperature	number	Temperature for generation (higher = more creative).	0 ≤ n ≤ 2 · default: 0.7
repetition_penalty	number	Repetition penalty (>= 1.1 required for stable generations).	1.1 ≤ n ≤ 2 · default: 1.2

Validate a payload

before you spend tokens

shell

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