GET

/v1/schemas/fal/audio/fal-ai%2Fpersonaplex%2Frealtime

kind inputactivity audiohash 3aede56fextracted Jul 6, 2026version currentsource upstream spec ↗

Request body

9 properties · 1 required · 0 $defs
propertytypedescriptionconstraints
audio*stringInput audio chunk (PCM s16le, 24kHz mono). Base64-encoded in JSON transport.format: binary
top_k_audiointegerTop-K sampling for audio tokens.1 ≤ n ≤ 2048 · default: 250
promptstringText prompt describing the AI persona and conversation context.default: "You are a wise and friendly tea…
seedintegerRandom seed for reproducibility.nullable
temperature_textnumberText sampling temperature. Higher values produce more diverse outputs.0 ≤ n ≤ 2 · default: 0.7
top_k_textintegerTop-K sampling for text tokens.1 ≤ n ≤ 1000 · default: 25
voice_audio_urlstringURL 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
voiceenumVoice 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"
temperature_audionumberAudio sampling temperature. Higher values produce more diverse outputs.0 ≤ n ≤ 2 · default: 0.8

Validate a payload

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