API Reference

Speech To Text Translate · WebSocket

WSSwss://stream.shabd.tech/v1/speech-to-text-translate

Connection headers

x-api-keystringrequired
API key for authentication.

Message flow

Outgoing Message (↑): The client sends metadata first then sends audio data in bytes.
Incoming Message (↓): The server responds json with requestId, status, transcript, translation, chunk, completed, mode.

Send Metadata (↑):

{  "requestId": "a216e43a-9d81-444c-a9ae-3c1e400fcb02",  "sourceLanguage": "hindi",  "targetLanguage": "tamil",  "sampleRate": 16000,  "projectId": "<your-project-id-here>"}

Send Audio Data (↑):

  Raw PCM 16-bit Audio Data (in Bytes)

Initial messageapplication/json

requestIdstringrequired
Unique identifier for the request
sourceLanguagestringrequired
Source language of the speech
targetLanguagestringrequired
Target Language of the text
sampleRatenumber or nulloptional
Sample Rate of the speech
Default:
16000
projectIdstring or nulloptional
An optional ID representing the project.

Server messages

101The server streams transcribed and translated text.

Receive Transcription and Translation (↓):

{  "requestId": "a216e43a-9d81-444c-a9ae-3c1e400fcb02",  "status": true,  "transcript": "नमस्ते, आपका दिन शुभ हो!",  "chunk": 1,  "completed": false,  "mode": "stt"}

{  "requestId": "a216e43a-9d81-444c-a9ae-3c1e400fcb02",  "status": true,  "translation": "வணக்கம் இனிய நாள்!",  "chunk": 1,  "completed": false,  "mode": "ttt"}

When the transcription is complete:

{  "requestId": "a216e43a-9d81-444c-a9ae-3c1e400fcb02",  "status": true,  "transcript": "",  "chunk": 2,  "completed": true,  "mode": "stt"}

When the translation is complete:

{  "requestId": "a216e43a-9d81-444c-a9ae-3c1e400fcb02",  "status": true,  "translation": "",  "chunk": 2,  "completed": true,  "mode": "ttt"}

Messages

Message Type	Example	Description
Send (↑)	`{ "requestId": "a216e43a-9d81-444c-a9ae-3c1e400fcb02", "sourceLanguage": "hindi", "targetLanguage": "tamil", "sampleRate": 16000, "projectId": "<your-project-id-here>" }`	The client sends parameters for getting transcription and translation from the Audio.
Send (↑)	`Raw PCM 16-bit Audio Data (in Bytes)`	The client sends audio data after sending metadata.
Receive (↓)	`{ "requestId": "a216e43a-9d81-444c-a9ae-3c1e400fcb02", "status": true, "transcript": "नमस्ते, आपका दिन शुभ हो!!", "chunk": 1, "completed": false, "mode": "stt" }`	The server sends transcription along with status and progress updates.
Receive (↓)	`{ "requestId": "a216e43a-9d81-444c-a9ae-3c1e400fcb02", "status": true, "translation": "வணக்கம் இனிய நாள்!", "chunk": 1, "completed": false, "mode": "ttt" }`	The server sends translation along with status and progress updates.
Receive (↓)	`{ "requestId": "a216e43a-9d81-444c-a9ae-3c1e400fcb02", "status": true, "transcript": "", "chunk": 2, "completed": true, "mode": "stt" }`	The server sends completed message for transcription.
Receive (↓)	`{ "requestId": "a216e43a-9d81-444c-a9ae-3c1e400fcb02", "status": true, "translation": "", "chunk": 2, "completed": true, "mode": "ttt" }`	The server sends completed message for translation.

Example response

{  "requestId": "a216e43a-9d81-444c-a9ae-3c1e400fcb02",  "status": true,  "transcript": "नमस्ते, आपका दिन शुभ हो!",  "chunk": 1,  "completed": false,  "mode": "stt"} {  "requestId": "a216e43a-9d81-444c-a9ae-3c1e400fcb02",  "status": true,  "translation": "வணக்கம் இனிய நாள்!",  "chunk": 1,  "completed": false,  "mode": "ttt"} {  "requestId": "a216e43a-9d81-444c-a9ae-3c1e400fcb02",  "status": true,  "transcript": "",  "chunk": 2,  "completed": true,  "mode": "stt"} {  "requestId": "a216e43a-9d81-444c-a9ae-3c1e400fcb02",  "status": true,  "translation": "",  "chunk": 2,  "completed": true,  "mode": "ttt"}

Request

1from websockets.sync.client import connect2from scipy.io import wavfile3import json4 5api_key = "your_api_key"6 7url = f'wss://stream.shabd.tech/v1/speech-to-text-translate'8headers = {"x-api-key": api_key} 9 10sampleRate, audio_data = wavfile.read("path_to_your_audio_file.wav")11audio_data_bytes = audio_data.tobytes() # Ensure your audio is Raw PCM 16 bit Format12 13metadata = {14    "requestId": "your_uuid_here",15    "sourceLanguage": "hindi",16    "targetLanguage": "tamil",17    "sampleRate": sampleRate,18    "projectId": "your_project_id_here"19}20 21with connect(url, additional_headers=headers) as ws:22    ws.send(json.dumps(metadata))23    ws.send(audio_data_bytes)24 25    for data in ws:26        response = json.loads(data)27        28        status = response.get("status", False)29        transcript = response.get("transcript", "")30        translation = response.get("translation", "")31        chunk = response.get("chunk") 32        completed = response.get("completed", False)33        mode = response.get("mode")34        35        if not status:36            print("Request Failed: ",response.get('message', 'Unknown Error'))37            break38        if transcript:39            print(f"Transcript {chunk}: {transcript}") # chunk id and transcript40        if completed and mode == "stt":41            print("Transcription completed")42        if translation:43            print(f"Translation {chunk}: {translation}") # chunk id and translation44        if completed and mode == "ttt":45            print("Translation completed")46            break

1const WebSocket = require('ws');2const fs = require('fs');3 4const api_key = "your_api_key";5const url = `wss://stream.shabd.tech/v1/speech-to-text-translate`; 6const headers = {7  "x-api-key": api_key8};9 10const audioFilePath = 'path_to_your_audio_file.wav';11const audioData = fs.readFileSync(audioFilePath);12const sampleRate = audioData.readUInt32LE(24);  // Extract sample rate from audio file13const pcmData = audioData.slice(44); // Sending raw PCM Audio14 15const metadata = {16  requestId: "your_uuid_here",17  sourceLanguage: "hindi",18  targetLanguage: "tamil",19  sampleRate: sampleRate,20  projectId: "your_project_id_here"21};22 23// Initialize WebSocket connection24const ws = new WebSocket(url, {25  headers: headers26});27 28ws.on('open', () => {29  ws.send(JSON.stringify(metadata));  30  ws.send(pcmData);               31});32 33ws.on('message', (data) => {34  if (Buffer.isBuffer(data)) {35    try {36      const stringData = data.toString('utf8');37      if (stringData && stringData.startsWith("{") && stringData.endsWith("}")) {38        const response = JSON.parse(stringData);39        40        status = response.status;41        transcript = response.transcript;42        translation = response.translation;43        chunk = response.chunk;44        completed = response.completed;45        mode = response.mode;46        47        if (!status) 48          console.log("Request Failed: ", response.message || 'Unknown Error');49  50        if (transcript) 51          console.log(`Transcript ${chunk}: ${transcript}`);52        53        if (completed && mode === "stt") 54          console.log("Transcription completed");55        56        if (translation) 57          console.log(`Translation ${chunk}: ${translation}`);58        59        if (completed && mode === "ttt") {60          console.log("Translation completed");61          ws.close();62        }63      } 64    } catch (err) {65      console.log("Error processing buffer: ", err);66    }67  } else {68    console.log("Unexpected data type received");69  }70});71 72ws.onerror = (error) => console.error('WebSocket error:', error);73ws.onclose = () => console.log('WebSocket connection closed');