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.

POST /v1/realtime/tts-stream

JavaScript

Stream and play audio chunks (Browser)

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);

200

"00000000: 52 49 46 46 FF FF FF FF 57 41 56 45 66 6D 74 20 "

Authorizations

Authorization · string · header · required

Pass the API key in the Authorization header, You need to put Token keyword before the API key. e.g. 'Authorization: Token '

Body

application/json

text · string · required

The text to be generated as an aduio file.

Example:

"مرحباً بكم في جميعاً في همسة!"

speaker · string · required

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.

Example:

"Amjad"

dialect · enum<string>

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

Available options: pls, egy, syr, irq, jor, leb, ksa, uae, bah, qat, kuw, oma, msa, ar-sa, en

Example:

"pls"

mulaw · boolean · default: false

Whether to use 'Mu-Law' algorithm in voice signal processing or not.

Example:

false

Response

200

stream

Streamed Successful Response - Chunked

The response is of type file.