GET

/v1/schemas/fal/audio/xai%2Ftts%2Fv1

kind inputactivity audiohash 9b7696f8extracted Jul 6, 2026version currentsource upstream spec ↗

Request body

4 properties · 1 required · 1 $defs
propertytypedescriptionconstraints
text*stringThe text to convert to speech. Maximum 15,000 characters. Supports speech tags for expressive delivery: inline tags like [laugh], [pause], [sigh] and wrapping tags like <whisper>text</whisper>, <slow>text</slow>.length ≥ 1 · length ≤ 15000
output_formatOutputFormatOutput format configuration. Defaults to MP3 at 24 kHz / 128 kbps.
voiceenumVoice to use for synthesis. eve: energetic, upbeat. ara: warm, friendly. rex: confident, clear. sal: smooth, balanced. leo: authoritative, strong.eve | ara | rex | sal | leo · default: "eve"
languageenumBCP-47 language code or 'auto' for automatic detection. Supported: en, zh, fr, de, hi, id, it, ja, ko, pt-BR, pt-PT, ru, es-MX, es-ES, tr, vi, bn, ar-EG, ar-SA, ar-AE.auto | en | ar-EG | ar-SA | ar-AE | bn · +15 more · default: "auto"

Validate a payload

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