> ## Documentation Index > Fetch the complete documentation index at: https://nadsoft.mintlify.site/llms.txt > Use this file to discover all available pages before exploring further. # Generate Streamed Text to Speech File Data > From the user's perspective, this is a standard request. In the response, we include specific headers: 'Transfer-Encoding' is set to 'chunked' to enable streaming, 'Connection' is set to 'keep-alive' to maintain the connection, and 'Content-Type' is set to 'audio/wav' to indicate the media type. These headers allow the client to stream audio data from the server in real time. Important Note: after collecting the chunks, you need to add the wav header manually to the data. If you wish to get a wav header, please use the [Generate TTS File Data API](/api-reference/endpoint/rt-generate-tts) ## OpenAPI ````yaml POST /v1/realtime/tts-stream openapi: 3.0.1 info: title: Hamsa API description: Trying out our transcription and media-to-text APIs license: name: MIT version: 1.0.0 servers: - url: https://api.tryhamsa.com security: [] paths: /v1/realtime/tts-stream: post: summary: Generates a streamed audio file from a text string. description: >- From the user's perspective, this is a standard request. In the response, we include specific headers: 'Transfer-Encoding' is set to 'chunked' to enable streaming, 'Connection' is set to 'keep-alive' to maintain the connection, and 'Content-Type' is set to 'audio/wav' to indicate the media type. These headers allow the client to stream audio data from the server in real time. Important Note: after collecting the chunks, you need to add the wav header manually to the data. If you wish to get a wav header, please use the [Generate TTS File Data API](/api-reference/endpoint/rt-generate-tts) requestBody: content: application/json: schema: $ref: '#/components/schemas/RtTtsRequest' responses: '200': description: Streamed Successful Response - Chunked content: stream: schema: type: string format: binary example: '00000000: 52 49 46 46 FF FF FF FF 57 41 56 45 66 6D 74 20 ' x-streaming: true headers: Transfer-Encoding: description: >- Indicates that the response uses chunked transfer encoding - streamed. schema: type: string example: chunked Connection: description: >- Indicates that the server will keep the connection open for streaming. schema: type: string example: keep-alive '400': description: Bad request content: application/json: schema: $ref: '#/components/schemas/ErrorSchema' '401': description: Unauthorized content: application/json: schema: $ref: '#/components/schemas/ErrorSchema' '500': description: Server Side Error content: application/json: schema: $ref: '#/components/schemas/ErrorSchema' security: - ApiKeyAuth: [] x-codeSamples: - lang: JavaScript label: Stream and play audio chunks (Browser) source: |- fetch('https://api.tryhamsa.com/v1/realtime/tts-stream', { method: 'POST', headers: { 'Content-Type': 'application/json', 'Authorization': 'Token YOUR_API_KEY' }, body: JSON.stringify({ speaker: 'Ali', dialect: 'pls', text: 'Hello, world!', mulaw: false }) }) .then(response => { const reader = response.body.getReader(); const chunks = []; function read() { reader.read().then(({ done, value }) => { if (done) { // Concatenate chunks and play entire stream const blob = new Blob(chunks, { type: 'audio/wav' }); const url = URL.createObjectURL(blob); const audio = new Audio(url); audio.play(); return; } chunks.push(value); read(); }); } read(); }) .catch(console.error); - lang: JavaScript label: Stream and save audio (Node.js) source: |- // For Node.js environments // npm install node-fetch import fetch from 'node-fetch'; import * as fs from 'fs'; fetch('https://api.tryhamsa.com/v1/realtime/tts-stream', { method: 'POST', headers: { 'Content-Type': 'application/json', 'Authorization': 'Token YOUR_API_KEY' }, body: JSON.stringify({ speaker: 'Ali', dialect: 'pls', text: 'Hello, world!', mulaw: false }) }) .then(response => { if (!response.ok) { throw new Error(`HTTP error! Status: ${response.status}`); } // Create a write stream for the output file const fileStream = fs.createWriteStream('hamsa-output.wav'); // Pipe the response body directly to the file response.body.pipe(fileStream); return new Promise((resolve, reject) => { response.body.on('error', reject); fileStream.on('finish', resolve); }); }) .then(() => { console.log('Audio saved to hamsa-output.wav'); }) .catch(console.error); components: schemas: RtTtsRequest: type: object properties: text: type: string description: The text to be generated as an aduio file. example: مرحباً بكم في جميعاً في همسة! speaker: type: string description: >- The speaker name, Suggestions: Amjad, Lyali, Salma, Mariam, Dalal, Lana, Jasem, Samir, Carla, Nada, or you can provide another values from the voice agents dashboard. You can also provide your own cloned voice's id here in the speaker field, but you need to preload that voice into the system first from [here](/api-reference/endpoint/preload-cloned-tts-voice) example: Majd dialect: type: string enum: - pls - egy - syr - irq - jor - leb - ksa - uae - bah - qat - msa description: >- The dialect of each country by its country code. Recommended voices per dialect are: pls (Palestinian): Amjad, Layan, Talin, Rema, Ali; leb (Lebanese): Carla, Majd; jor (Jordanian): Lana, Jasem, Nada, Sarah; syr (Syrian): Dalal, Mais; ksa (Saudi): Hiba, Khadija, Fahd, Jasem; bah (Bahraini): Mazen, Ruba; uae (Emirati): Salma, Dima; egy (Egyptian): Mariam, Samir, Nada, Ali, Ahmed; irq (Iraqi): Lyali, Fatma. example: pls mulaw: type: boolean description: Whether to use 'Mu-Law' algorithm in voice signal processing or not. example: false default: false required: - text - speaker ErrorSchema: type: object properties: code: type: integer message: type: string securitySchemes: ApiKeyAuth: type: apiKey in: header name: Authorization description: >- Pass the API key in the Authorization header, You need to put Token keyword before the API key. e.g. 'Authorization: Token ' ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.