Text-to-Speech

Turn text into natural‑sounding audio. Like STT, TTS runs as an asynchronous job; the synthesised audio is attached to the finished job.

POST /v1/tts/jobs API key

JSON body

`text` * string	The text (or SSML) to synthesise.
`voice` string	Voice identifier.
`languageCode` string	e.g. "lo-LA".
`format` mp3 \| wav \| ogg	Output audio format. Default: mp3.
`ssml` boolean	Set true if text is SSML. Default: false.
`speakingRate` number	Speed multiplier, e.g. 1.0.
`pitch` number	Pitch adjustment, e.g. 0.0.

Enqueue a job

curl -X POST https://api-ocr.vanguardinitiative.com/v1/tts/jobs \
  -H "authorization: Bearer $API_KEY" \
  -H 'content-type: application/json' \
  -d '{"text":"ສະບາຍດີ","languageCode":"lo-LA","format":"mp3"}'

const res = await fetch('https://api-ocr.vanguardinitiative.com/v1/tts/jobs', {
  method: 'POST',
  headers: {
    authorization: 'Bearer ' + API_KEY,
    'content-type': 'application/json',
  },
  body: JSON.stringify({ text: 'ສະບາຍດີ', languageCode: 'lo-LA', format: 'mp3' }),
});
const { jobId } = await res.json();

202 Job accepted

{
  "status": "success",
  "jobId": "9a2b7c10-...",
  "state": "pending"
}

Poll GET /v1/jobs/{id} until it finishes; the stored audio is referenced in the job’s result.