GET

/v1/schemas/byteplus/audio/tts%2Fcreate

kind inputactivity audiohash f021b8c7…extracted Aug 15, 2026version currentsource upstream spec ↗

Request body

5 properties · 2 required · 2 $defs
propertytypedescriptionconstraints
model*stringSeed Speech synthesis model, e.g. seed-audio-1.0.
text_prompt*stringThe text to speak. Dual-purpose: literal text or a natural-language description of the delivery, and where the @Audio1..@Audio3 reference markers go. (The field is text_prompt, not text — the 'text' spelling belongs to the separate /tts/unidirectional endpoint…length ≤ 3000
referencesTTSReference[]
audio_configTTSAudioConfigAudio output configuration. The *_rate fields are integer percentages relative to the voice's neutral delivery, not multipliers.
watermarkobjectWatermark the generated audio. NOT a boolean: `true` and a bare string both fail with 500 `55000000 kiteX processing … thrift marshal`, while an object is accepted with 200 — so the wire type is a struct. Its member names could not be confirmed (an unrecognise…

Validate a payload

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