Connecting…
Pakistan ki apni Urdu Neural TTS

اردو لکھیں،
قدرتی آواز سنیں

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.

اپنی پہچان، اپنی آواز
Last latency
· ms
Server side inference
Concurrency
20 max
Parallel requests handled
Avg (last run)
· ms
Across concurrent batch
Success rate
·
Completed synthesis
اردو متن 0 / 2000
Slow 0.5× → Normal 1.0× → Fast 2.0×
Latest output Generated in · ms  ·  · chars
0:00 / 0:00
Concurrent Load Test
Ek saath kai requests bhej kar latency aur throughput dekhein
Concurrent requests:
Running…
·
Avg latency
·
Min latency
·
Max latency
·
Success rate
Generation history
No generations yet

Overview

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.

Base URL
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.

Authentication

Authenticate your requests by including your API key in the X-API-Key header.

Enter your API key above and all code examples will update automatically. Contact your administrator to get an API key.
HeaderValueRequired
X-API-KeyYour secret API keyRequired
Content-Typeapplication/jsonRequired

Alternatively, pass the key as a Bearer token:

Authorization: Bearer hmnv-your-api-key

POST /v1/tts/synthesize

Convert Urdu text to speech. Returns a WAV audio file.

POST http://34.93.31.201:8000/v1/tts/synthesize

Request Body

ParameterTypeRequiredDefaultDescription
modelstringRequired·Model ID. Must be humnava-v2
textstringRequired·Urdu text to synthesize. Max 2000 chars.
noise_scalefloatOptional0.667Pronunciation variety. Range 0 to 1.
length_scalefloatOptional1.0Duration multiplier. 0.5 = 2× faster, 2.0 = 2× slower.
noise_scale_wfloatOptional0.8Rhythm variation. Range 0 to 1.

Response

Returns audio/wav binary data with the following headers:

HeaderDescription
X-Request-IdUnique request identifier (e.g. req_a3f8b2c1d4e5)
X-ModelModel used for synthesis (humnava-v2)
X-Latency-MsServer side inference time in milliseconds
X-Text-CharsNumber of characters in the input text

Code Examples

Models

Currently one model is available. Additional models will be released in future versions.

Model IDLanguageSample RateDescription
humnava-v2 Urdu (ur) 22,050 Hz High-quality neural TTS. Single speaker, female voice. Trained on 30+ hours of studio audio.

List Models

GET http://34.93.31.201:8000/v1/models
curl http://34.93.31.201:8000/v1/models

Error Codes

The API uses standard HTTP status codes. Error responses include a JSON body with an error object.

{ "error": { "code": "rate_limit_exceeded", "message": "Max 3 concurrent requests. Retry shortly.", "type": "rate_limit_error" } }
HTTP StatusError CodeCause
401missing_api_keyNo API key provided in request headers
401invalid_api_keyAPI key is incorrect or has been deactivated
400invalid_modelModel ID is not recognized
422·Request body validation failed (missing field or wrong type)
429rate_limit_exceededServer is at max capacity (3 concurrent). Retry after a moment.
500inference_errorInternal model error during synthesis