On premise Urdu speech recognition, banaya gaya Pakistani zameen par. Mic se record karein ya audio file upload karein — saaf Urdu transcript wapas milega. Sab kuch aapke apne infrastructure par.
Callrolin STT API provides on-premise Urdu speech-to-text. Send an audio file and receive a clean transcript in a JSON response. Also supports Punjabi, Sindhi, Pashto and English, plus translation to English.
http://34.93.31.201:8000
Requests use multipart/form-data (audio upload) and return an application/json transcript. 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 | multipart/form-data | Required |
Alternatively, pass the key as a Bearer token:
Convert an audio file to text. Returns a JSON transcript.
| Field | Type | Required | Default | Description |
|---|---|---|---|---|
file | binary | Required | · | Audio file. WAV, MP3, M4A, OGG, WEBM, FLAC. Max 25 MB. |
model | string | Required | · | Model ID. Must be samaat-v1 |
language | string | Optional | ur | ISO code: ur, pa, sd, ps, en, or auto. |
task | string | Optional | transcribe | transcribe or translate (to English). |
Returns application/json:
Currently one model is available. Additional models will be released in future versions.
| Model ID | Languages | Sample Rate | Description |
|---|---|---|---|
samaat-v1 |
Urdu, Punjabi, Sindhi, Pashto, English | 16,000 Hz | On-premise Urdu-first ASR. Handles noisy phone audio and code-switching. Optional English translation. |
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 |
| 400 | no_audio_file | No file field in the request |
| 413 | file_too_large | Audio exceeds the 25 MB limit |
| 415 | unsupported_media | Audio format could not be decoded |
| 500 | inference_error | Internal model error during transcription |