GET

/v1/schemas/fal/audio/fal-ai%2Fzonos2

kind inputactivity audiohash 25ecbee3extracted Jul 6, 2026version currentsource upstream spec ↗

Request body

11 properties · 1 required · 0 $defs
propertytypedescriptionconstraints
reference_audio_url*stringReference audio to clone the voice from.
textstringText to synthesize in the cloned voice.default: "\"Fal\" is the fastest solution…
clean_speaker_backgroundbooleanMark the reference audio as having a clean background.default: false
seedintegerSeed for reproducibility. Random when omitted.0 ≤ n ≤ 2147483647 · nullable
languagestringText-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_kintegerTop-k sampling cutoff (0 disables).0 ≤ n ≤ 2048 · default: 106
temperaturenumberSampling temperature.0 ≤ n ≤ 2 · default: 1.15
top_pnumberNucleus sampling probability (0 disables).0 ≤ n ≤ 1 · default: 0
min_pnumberMinimum-probability sampling threshold.0 ≤ n ≤ 1 · default: 0.18
accurate_modebooleanTrue = closer voice match; False = more expressive.default: true
max_tokensintegerMaximum number of audio frames to generate. Defaults to the model context limit.1 ≤ n ≤ 6144 · nullable

Validate a payload

before you spend tokens
shell
$ curl -X POST https://modelschemas.com/v1/validate \
    -d '{"provider":"fal","endpointId":"fal-ai/zonos2","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}