Voice Cloned TTS (Streaming)

curl -X POST https://api.vachana.ai/api/v1/tts/sse \
  -H "X-API-Key-ID: your-api-key-id" \
  -H "Content-Type: application/json" \
  -H "Accept: text/event-stream" \
  -N \
  -d '{
    "text": "नमस्ते, आप कैसे हैं?",
    "model": "vachana-vc-v1",
    "audio_config": {
      "sample_rate": 44100,
      "encoding": "linear_pcm",
      "container": "wav"
    },
    "speaker_embedding": {
      "embedding": "your-embedding-string",
      "shape": [1, 768],
      "dtype": "torch.bfloat16"
    }
  }'

import requests
import base64
import json

url = "https://api.vachana.ai/api/v1/tts/sse"
headers = {
    "X-API-Key-ID": "your-api-key-id",
    "Content-Type": "application/json",
    "Accept": "text/event-stream"
}
payload = {
    "text": "नमस्ते, आप कैसे हैं?",
    "model": "vachana-vc-v1",
    "audio_config": {
        "sample_rate": 44100,
        "encoding": "linear_pcm",
        "container": "wav"
    },
    "speaker_embedding": {
        "embedding": "your-embedding-string",
        "shape": [1, 768],
        "dtype": "torch.bfloat16"
    }
}

response = requests.post(url, headers=headers, json=payload, stream=True)

audio_chunks = []
for line in response.iter_lines():
    if line:
        line = line.decode('utf-8')
        if line.startswith('data: '):
            event = json.loads(line[6:])
            if event.get("audio"):
                # Audio chunk (base64)
                audio_chunks.append(base64.b64decode(event["audio"]))
            if event.get("is_final"):
                print("Stream completed")
                break

# Combine and save audio
with open("audio.wav", "wb") as f:
    for chunk in audio_chunks:
        f.write(chunk)
print("Audio saved successfully")

const url = "https://api.vachana.ai/api/v1/tts/sse";
const headers = {
  "X-API-Key-ID": "your-api-key-id",
  "Content-Type": "application/json",
  "Accept": "text/event-stream"
};
const payload = {
  text: "नमस्ते, आप कैसे हैं?",
  model: "vachana-vc-v1",
  audio_config: {
    sample_rate: 44100,
    encoding: "linear_pcm",
    container: "wav"
  },
  speaker_embedding: {
    embedding: "your-embedding-string",
    shape: [1, 768],
    dtype: "torch.bfloat16"
  }
};

const eventSource = new EventSource(url);
const audioChunks = [];

eventSource.addEventListener("chunk", (event) => {
  const payload = JSON.parse(event.data);
  if (payload.audio) {
    const audioData = atob(payload.audio);
    const bytes = new Uint8Array(audioData.length);
    for (let i = 0; i < audioData.length; i++) {
      bytes[i] = audioData.charCodeAt(i);
    }
    audioChunks.push(bytes);
  }
});

eventSource.addEventListener("complete", (event) => {
  console.log("Stream complete");
  
  // Combine chunks and create blob
  const blob = new Blob(audioChunks, { type: "audio/wav" });
  const url = window.URL.createObjectURL(blob);
  const a = document.createElement("a");
  a.href = url;
  a.download = "audio.wav";
  a.click();
  
  eventSource.close();
});

eventSource.onerror = (error) => {
  console.error("SSE Error:", error);
  eventSource.close();
};

// Send the request
fetch(url, {
  method: "POST",
  headers: headers,
  body: JSON.stringify(payload)
});