GET
/v1/schemas/fal/audio/fal-ai%2Fpersonaplex%2Frealtime
Accept:
Request body
9 properties · 1 required · 0 $defs| property | type | description | constraints |
|---|---|---|---|
| audio* | string | Input audio chunk (PCM s16le, 24kHz mono). Base64-encoded in JSON transport. | format: binary |
| top_k_audio | integer | Top-K sampling for audio tokens. | 1 ≤ n ≤ 2048 · default: 250 |
| prompt | string | Text prompt describing the AI persona and conversation context. | default: "You are a wise and friendly tea… |
| seed | integer | Random seed for reproducibility. | nullable |
| temperature_text | number | Text sampling temperature. Higher values produce more diverse outputs. | 0 ≤ n ≤ 2 · default: 0.7 |
| 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 |
| 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" |
| temperature_audio | number | Audio sampling temperature. Higher values produce more diverse outputs. | 0 ≤ n ≤ 2 · default: 0.8 |
Validate a payload
before you spend tokensshell
$ curl -X POST https://modelschemas.com/v1/validate \
-d '{"provider":"fal","endpointId":"fal-ai/personaplex/realtime","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}