GET

/v1/schemas/fal/audio/fal-ai/personaplex

Accept:

kind inputactivity audiohash 3f1e1e74…extracted Oct 9, 2026version currentsource upstream spec ↗

field	recorded source
schema	Source linked above. upstream-spec Source trace `313aef59792f0d6c64594cf4d835f5d1e72820cacacd8e34fb15c2a2039d03bf` { "fetchedAt": 1791522002, "extractorVersion": "1", "verifiedAt": null }

Request body

10 properties · 1 required · 0 $defs

property	type	description	constraints
audio_url*	string	URL to the input audio file (user's speech).
temperature_text	number	Text sampling temperature. Higher values produce more diverse outputs.	0 ≤ n ≤ 2 · default: 0.7
prompt	string	Text prompt describing the AI persona and conversation context.	default: "You are a wise and friendly tea…
temperature_audio	number	Audio sampling temperature. Higher values produce more diverse outputs.	0 ≤ n ≤ 2 · default: 0.8
voice	enum	Voice ID for the AI response. NAT = natural, VAR = variety. F = female, M = male. Ignored when voice_audio_url is provided.	NATF0 \| NATF1 \| NATF2 \| NATF3 \| NATM0 \| NATM1 · +12 more · default: "NATF2"
seed	integer	Random seed for reproducibility.	nullable
top_k_text	integer	Top-K sampling for text tokens.	1 ≤ n ≤ 1000 · default: 25
voice_audio_url	string	URL to a voice sample audio for on-the-fly voice cloning. When provided, the AI responds in the cloned voice instead of the preset 'voice'. 10+ seconds of clear speech recommended. Billed at 2x rate.	nullable
enable_safety_checker	boolean	Authorized callers may set false to request relaxed screening.	default: true
top_k_audio	integer	Top-K sampling for audio tokens.	1 ≤ n ≤ 2048 · default: 250

Validate a payload

before you spend tokens

shell

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