GET
/v1/schemas/fal/audio/fal-ai%2Fzonos2
Accept:
Request body
11 properties · 1 required · 0 $defs| property | type | description | constraints |
|---|---|---|---|
| reference_audio_url* | string | Reference audio to clone the voice from. | |
| text | string | Text to synthesize in the cloned voice. | default: "\"Fal\" is the fastest solution… |
| clean_speaker_background | boolean | Mark the reference audio as having a clean background. | default: false |
| seed | integer | Seed for reproducibility. Random when omitted. | 0 ≤ n ≤ 2147483647 · nullable |
| language | string | Text-normalization language code. Supported: en_us, en_gb, fr_fr, de, es, it, pt_br, ja, cmn, ko. Unsupported codes skip normalization. | default: "en_us" |
| top_k | integer | Top-k sampling cutoff (0 disables). | 0 ≤ n ≤ 2048 · default: 106 |
| temperature | number | Sampling temperature. | 0 ≤ n ≤ 2 · default: 1.15 |
| top_p | number | Nucleus sampling probability (0 disables). | 0 ≤ n ≤ 1 · default: 0 |
| min_p | number | Minimum-probability sampling threshold. | 0 ≤ n ≤ 1 · default: 0.18 |
| accurate_mode | boolean | True = closer voice match; False = more expressive. | default: true |
| max_tokens | integer | Maximum number of audio frames to generate. Defaults to the model context limit. | 1 ≤ n ≤ 6144 · nullable |
Validate a payload
before you spend tokensshell
$ curl -X POST https://modelschemas.com/v1/validate \
-d '{"provider":"fal","endpointId":"fal-ai/zonos2","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}