GET

/v1/schemas/fal/audio/heygen/heygen-voice

Accept:

kind inputactivity audiohash a93f99e9…extracted Nov 10, 2026version currentsource upstream spec ↗

field	recorded source
schema	Source linked above. upstream-spec Source trace `24b8b16f286e838c1fe7218627917e82740737d67559b5e38e5ea0ee72ca89a5` { "fetchedAt": 1794286801, "extractorVersion": "2", "verifiedAt": null }

Request body

6 properties · 1 required · 0 $defs

property	type	description	constraints
text*	string	The text to speak.	length ≥ 1 · length ≤ 5000
expressiveness_boost	number	How expressive the delivery is.	0 ≤ n ≤ 1 · default: 1
enable_safety_checker	boolean	Authorized callers may set false to request relaxed screening.	default: true
language	enum	Language of the text. Detected from the text when omitted.	ar \| be \| bg \| ca \| cs \| da · +33 more · nullable
reference_audio_url	string	Recording of a single speaker to clone instead of using a public voice. Only the first 3 minutes are used.	nullable
voice	enum	HeyGen public voice. Ignored when reference_audio_url is set.	Jonah \| Nadine \| Tabitha \| Soren \| Elowen \| Vincent · +18 more · default: "Jonah"

Validate a payload

before you spend tokens

shell

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