GET

/v1/schemas/fal/audio/fal-ai%2Fchatterbox%2Ftext-to-speech%2Fmultilingual

kind inputactivity audiohash 1369e90cextracted Jul 6, 2026version currentsource upstream spec ↗

Request body

7 properties · 1 required · 0 $defs
propertytypedescriptionconstraints
text*stringThe text to be converted to speech (maximum 300 characters). Supports 23 languages including English, French, German, Spanish, Italian, Portuguese, Hindi, Arabic, Chinese, Japanese, Korean, and more.length ≤ 300
custom_audio_languageenumIf using a custom audio URL, specify the language of the audio here. Ignored if voice is not a custom url.english | arabic | danish | german | greek | spanish · +17 more · nullable
exaggerationnumberControls speech expressiveness and emotional intensity (0.25-2.0). 0.5 is neutral, higher values increase expressiveness. Extreme values may be unstable.0.25 ≤ n ≤ 2 · default: 0.5
seedintegerRandom seed for reproducible results. Set to 0 for random generation, or provide a specific number for consistent outputs.nullable
temperaturenumberControls randomness and variation in generation (0.05-5.0). Higher values create more varied speech patterns.0.05 ≤ n ≤ 5 · default: 0.8
cfg_scalenumberConfiguration/pace weight controlling generation guidance (0.0-1.0). Use 0.0 for language transfer to mitigate accent inheritance.0 ≤ n ≤ 1 · default: 0.5
voicestringLanguage code for synthesis. In case using custom please provide audio url and select custom_audio_language.default: "english"

Validate a payload

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