GET

/v1/schemas/deepgram/audio/v2/speak

kind inputactivity audiohash 9a65711e…extracted Oct 24, 2026version currentsource upstream spec ↗
fieldrecorded source
schemaSource linked above.

upstream-spec

Source trace
f91de57c05631ad01baabd75ab7cb2938a1ef69e11b1449e05e3bf256838db99
{
  "fetchedAt": 1792819826,
  "extractorVersion": "1",
  "verifiedAt": null
}

Request body

1 properties · 1 required · 0 $defs
propertytypedescriptionconstraints
text*stringThe text content to be converted to speech. For English, German, Dutch, French, Hindi, Italian, Japanese, Portuguese, Russian and Spanish, the server normalizes the text (numbers, dates, abbreviations) before synthesis; the other languages are in Early Access …

Validate a payload

before you spend tokens
shell
$ curl -X POST https://modelschemas.com/v1/validate \
    -d '{"provider":"deepgram","endpointId":"v2/speak","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}