On premise Urdu voice synthesis, banaya gaya Pakistani zameen par. Native phonetics, kam latency, aur ek waqt mein kai calls. Sab kuch aapke apne infrastructure par.
Callrolin TTS API provides state-of-the-art Urdu text-to-speech synthesis, deployed on-premise. Send Urdu text and receive high-quality WAV audio in response.
http://34.93.31.201:8000
All API requests use JSON request bodies and return audio/wav responses. Authentication is required for all /v1/ endpoints.
Authenticate your requests by including your API key in the X-API-Key header.
| Header | Value | Required |
|---|---|---|
X-API-Key | Your secret API key | Required |
Content-Type | application/json | Required |
Alternatively, pass the key as a Bearer token:
Convert Urdu text to speech. Returns a WAV audio file.
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
model | string | Required | · | Model ID. Must be humnava-v2 |
text | string | Required | · | Urdu text to synthesize. Max 2000 chars. |
noise_scale | float | Optional | 0.667 | Pronunciation variety. Range 0 to 1. |
length_scale | float | Optional | 1.0 | Duration multiplier. 0.5 = 2× faster, 2.0 = 2× slower. |
noise_scale_w | float | Optional | 0.8 | Rhythm variation. Range 0 to 1. |
Returns audio/wav binary data with the following headers:
| Header | Description |
|---|---|
X-Request-Id | Unique request identifier (e.g. req_a3f8b2c1d4e5) |
X-Model | Model used for synthesis (humnava-v2) |
X-Latency-Ms | Server side inference time in milliseconds |
X-Text-Chars | Number of characters in the input text |
Currently one model is available. Additional models will be released in future versions.
| Model ID | Language | Sample Rate | Description |
|---|---|---|---|
humnava-v2 |
Urdu (ur) | 22,050 Hz | High-quality neural TTS. Single speaker, female voice. Trained on 30+ hours of studio audio. |
The API uses standard HTTP status codes. Error responses include a JSON body with an error object.
| HTTP Status | Error Code | Cause |
|---|---|---|
| 401 | missing_api_key | No API key provided in request headers |
| 401 | invalid_api_key | API key is incorrect or has been deactivated |
| 400 | invalid_model | Model ID is not recognized |
| 422 | · | Request body validation failed (missing field or wrong type) |
| 429 | rate_limit_exceeded | Server is at max capacity (3 concurrent). Retry after a moment. |
| 500 | inference_error | Internal model error during synthesis |