> ## Documentation Index > Fetch the complete documentation index at: https://docs.tryhamsa.com/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 /api-reference/openapi.json 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 (voice) name. Pick a voice that matches the chosen dialect — see the `dialect` field for voice examples per dialect. You can also pass the UUID of a custom cloned voice, but you must first preload it via the [Preload Cloned Voice endpoint](/src/api-reference/endpoint/preload-cloned-tts-voice). example: Amjad dialect: type: string enum: - pls - egy - syr - irq - jor - leb - ksa - uae - bah - qat - kuw - oma - msa - ar-sa - en description: >- The dialect to synthesize, identified by its country/region code. Voice examples per dialect: - `pls` (Palestinian) — Amjad, Layan - `egy` (Egyptian) — Mariam, Samir - `syr` (Syrian) — Dalal, Mais - `irq` (Iraqi) — Lyali, Fatma - `jor` (Jordanian) — Lana, Jasem - `leb` (Lebanese) — Carla, Majd - `ksa` (Saudi) — Hiba, Fahd - `uae` (Emirati) — Salma, Dima - `bah` (Bahraini) — Mazen, Ruba - `qat` (Qatari) — Deema, Faisal - `kuw` (Kuwaiti) — Mai, Hatem - `oma` (Omani) — Aisha, Jaber - `msa` (Modern Standard Arabic / Fusha) — Salem, Tamim - `ar-sa` (Arabic – Gulf) — Khalid, Rahma - `en` (English) — Emma, James example: pls mulaw: type: boolean description: Whether to use 'Mu-Law' algorithm in voice signal processing or not. example: false default: false sampleRate: type: string enum: - 8k - 16k description: >- Output sample rate of the PCM audio. Defaults to `16k`. Only applies to PCM output — cannot be combined with `mulaw` (mu-law output is always 8 kHz). default: 16k example: 16k expressiveness: type: number description: >- Controls how expressive the generated speech sounds. `0` is flat and monotone, `1` is the natural default, and `2` is highly expressive. minimum: 0 maximum: 2 default: 1 example: 1 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 ' ````