Text-to-Speech (TTS)
Generate natural-sounding speech from Twi text. Choose between male and female voices.
Endpoint
POST /synthesize
Request Body
| Field | Type | Description |
|---|---|---|
| text | string (required) | Twi text to synthesize |
| voice | string (required) | "male" or "female" |
Example
curl -X POST "https://api.ayaspeech.ayadata.ai/synthesize" \
-H "x-api-token: your_api_token" \
-H "Content-Type: application/json" \
-d '{"text": "Medɔ wo", "voice": "female"}' \
--output speech.wavResponse
Returns a WAV audio file directly. Content-Type: audio/wav
Inference time is returned in the X-Inference-Time response header.
Limits
| Tier | Daily Requests | Monthly Characters |
|---|---|---|
| Free | 3 | 15,000 |
| Premium | 1,000 | 2,000,000 |
Voices
| Voice | Description |
|---|---|
| female | Natural female voice, clear pronunciation |
| male | Natural male voice |