API Reference

Text To Speech · WebSocket

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

Connection headers

x-api-keystringrequired
API key for authentication.

Message flow

Outgoing Message (↑): The client sends a JSON object with the necessary parameters for speech synthesis.
Incoming Message (↓): The server responds with a stream of raw PCM-16 bit audio data in chunks.

Send Message (↑):

Sending Text Message

{  "requestId": "a216e43a-9d81-444c-a9ae-3c1e400fcb02",  "text": "नमस्ते, आपका दिन शुभ हो!",  "language": "hindi",  "gender": "female",  "sampleRate": 8000,  "speed": "normal"}

Initial messageapplication/json

requestIdstringrequired
Unique identifier for the request
textstringrequired
Text content to be converted to speech
languagestringrequired
Language of the text for synthesis
genderstringoptional
Allowed:
male
female
Default:
male
sampleRatenumber or nulloptional
Audio sample rate for synthesis (e.g., 22050)
speedstringoptional
Allowed:
slow
normal
fast
Default:
normal

Server messages

101The server sends back synthesized audio as continuous streams of raw PCM-16 bit audio data.The response consists of 48-byte header containing metadata.Raw PCM-16 bit audio data following the header.

Receive Message (↓):

Streaming PCM-16 bit audio data in chunks...

Field Breakdown

Field	Description	Size	Byte Offset
requestId	Unique ID for the request	36	0 - 35
status	0 (error) or 1 (success)	1	36
completed	0 (in progress) or 1 (finished)	1	37
sampleRate	Sampling rate of the audio (e.g., 8, 16, 22, 48)	1	38
gender	0 (female) or 1 (male)	1	39
contentLength	Length of the audio content (in bytes)	4	40 - 43
chunkId	ID for each audio chunk	1	44
Audio content begins from byte 48

Messages

Message Type	Example	Description
Send (↑)	`{ "requestId": "a216e43a-9d81-444c-a9ae-3c1e400fcb02", "text": "नमस्ते, आपका दिन शुभ हो!", "language": "hindi", "gender": "female", "sampleRate": 8000, "speed": "normal" }`	The client sends parameters for speech synthesis.
Receive (↓)	`Continuous stream of raw PCM-16 bit audio data in chunks until byte header completed true`	The server sends back the synthesized audio as PCM-16 bit.

Request

1from websockets.sync.client import connect2import json3import wave4 5api_key = "your_api_key"6 7url = f'wss://stream.shabd.tech/v1/text-to-speech'8headers = {"x-api-key": api_key}9 10sampleRate = 8000 # SampleRate for Audio Synthesis11metadata = {12    "requestId": 'your_uuid_here',13    "text": "नमस्ते, आपका दिन शुभ हो!",14    "language": "hindi",15    "gender": "female",16    "sampleRate": sampleRate,17    "speed": "normal"18}19 20with connect(url, additional_headers=headers) as ws:21    ws.send(json.dumps(metadata))22    23    i=124    for data in ws:25        if isinstance(data, bytes):26            header = data[:48]27            content = data[48:]  # Audio content starts from 4828            29            status = header[36] # status 0 or 130            completed = header[37] # completed 0 or 131            32            if not status: 33                print("Request Failed: ", str(content))34                break  35            print(f"Received audio chunk of size {len(content)} bytes")36            with wave.open(f'SynthesizedAudio_Chunk{i}.wav', 'wb') as wf:37                wf.setnchannels(1)38                wf.setsampwidth(2)39                wf.setframerate(sampleRate)40                wf.writeframes(content)41                i+=142            if completed: 43                print("Audio Synthesis Completed")44                break45        else:46            print("Request Failed")

1const WebSocket = require('ws');2const fs = require('fs');3const wav = require('wav');4 5const api_key = "your_api_key";6const url = `wss://stream.shabd.tech/v1/text-to-speech`; 7const headers = {8  "x-api-key": api_key9};10 11const sampleRate = 8000; // Sample Rate for Audio Synthesis12const metadata = {13  requestId: "your_uuid_here",14  text: "नमस्ते, आपका दिन शुभ हो!",15  language: "hindi",16  gender: "female",17  sampleRate: sampleRate,18  speed: "normal"19};20 21// Initialize WebSocket connection22const ws = new WebSocket(url, {23  headers: headers24});25 26ws.on('open', () => {27  ws.send(JSON.stringify(metadata));         28});29 30let i = 1;31ws.on('message', (data) => {32  if (Buffer.isBuffer(data)) {33    try {34        const header = data.slice(0, 48);  // first 48 bytes are header35        const content = data.slice(48);    // The rest is audio content36        const status = header[36]; // status 0 or 137        const completed = header[37]; // completed 0 or 138        39        if (!status) { 40          console.log("Request Failed: ", content.toString());41          ws.close(); 42        }43 44        console.log(`Received audio chunk of size ${content.length} bytes`);45 46        if (completed) { 47          console.log("Audio Synthesis Completed");48          ws.close(); 49        }50        51        const writer = new wav.Writer({52            sampleRate: sampleRate,  // Set the sample rate53            channels: 1,             // Mono (1 channel)54            bitDepth: 16             // 16-bit depth (common for audio)55          });56  57        const fileName = `SynthesizedAudio_Chunk${i}.wav`;58        const writeStream = fs.createWriteStream(fileName);59 60        writer.pipe(writeStream);61        writer.write(content);62        writer.end();63  64        console.log(`Saved audio chunk to ${fileName}`);65        i++; 66    } catch (err) {67      console.log("Error processing buffer: ", err);68    }69  } else {70    console.log("Unexpected data type received");71  }72});73 74ws.on('error', (err) => {75  console.error("WebSocket Error: ", err);76});77 78ws.on('close', () => {79  console.log("WebSocket connection closed");80});