Developer API Portal

Pronunciation REST API

Integrate text-to-speech audio streams, regional voice accents, and phonetic dictionary lookups directly into your web or mobile applications.

25 Req / Min Rate Limit

Per-IP sliding window rate limiting keeps service response times fast and consistent.

Direct MP3 Bytes

`POST /api/v1/pronunciations` returns raw `audio/mpeg` binary audio directly.

13 Languages Supported

Full support for US, UK, AU, IN English, Spanish, French, German, Japanese, Korean & Hindi.

POST/api/v1/pronunciations

Returns audio/mpeg stream

Synthesizes high-quality neural voice speech for any text string, returning an audio binary payload ready for instant web or mobile playback.

Request Parameters (JSON)

Field	Type	Required	Description
text	string	Yes	Text string to pronounce (1 to 300 chars).
language	string	Yes	Locale code e.g. `en-US`, `en-GB`, `en-IN`, `fr-FR`, `hi-IN`.
voice	string	Optional	Voice ID or gender e.g. `female`, `male`, `aria`, `guy`, `sonia`.
delivery	string	Optional	`natural` (default), `careful`, or `quick`.

Code Examples

curl -X POST http://localhost:5000/api/v1/pronunciations \
  -H 'Content-Type: application/json' \
  -H 'Accept: audio/mpeg' \
  -d '{
    "text": "Worcestershire",
    "language": "en-GB",
    "voice": "sonia",
    "delivery": "natural"
  }' \
  --output worcestershire.mp3

GET/api/v1/dictionary

Returns JSON Dictionary Object

Fetches dictionary senses, IPA phonetic notation, parts of speech, usage examples, and synonyms for a requested headword.

curl "http://localhost:5000/api/v1/dictionary?word=pronunciation&language=en"

Response Headers & Error Handling

Every response includes standard rate limit headers (X-RateLimit-Limit, X-RateLimit-Remaining) and TTS metadata (X-TTS-Provider, X-TTS-Voice). If rate limit is exceeded, HTTP status 429 Too Many Requests is returned.