Text-to-Speech API

# The response is binary audio data — save directly to file
curl -s -X POST "https://api.shisa.ai/tts" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"voice_id": "e3362c0a-7677-4cd8-b122-91fb093305c9", "format": "mp3", "text": "テスト"}' \
  --output speech.mp3

[
  {
    "id": "e3362c0a-7677-4cd8-b122-91fb093305c9",
    "description": "Young male Japanese voice...",
    "language": "Japanese & English",
    "gender": "Male",
    "formats": ["mp3", "ogg", "pcm"],
    "streaming": true
  }
]

# List available voices
curl -s -X GET "https://api.shisa.ai/tts/voices" \
  -H "Authorization: Bearer YOUR_API_KEY" | jq .

# Generate speech
curl -s -X POST "https://api.shisa.ai/tts" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "voice_id": "e3362c0a-7677-4cd8-b122-91fb093305c9",
    "format": "mp3",
    "stream": false,
    "text": "こんにちは。Shisa Talkへようこそ。"
  }' \
  --output speech.mp3

# Stream audio directly to a player
curl -s -X POST "https://api.shisa.ai/tts" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "voice_id": "e3362c0a-7677-4cd8-b122-91fb093305c9",
    "format": "mp3",
    "stream": true,
    "text": "ストリーミングテストです。"
  }' \
  --output - | ffplay -nodisp -autoexit -

import requests

API_URL = "https://api.shisa.ai"
API_KEY = "YOUR_API_KEY"
HEADERS = {
    "Authorization": f"Bearer {API_KEY}",
    "Content-Type": "application/json"
}

# List available voices
def list_voices():
    response = requests.get(f"{API_URL}/tts/voices", headers=HEADERS)
    return response.json()

# Generate speech
def generate_speech(text, voice_id="e3362c0a-7677-4cd8-b122-91fb093305c9", format="mp3", stream=False):
    response = requests.post(
        f"{API_URL}/tts",
        headers=HEADERS,
        json={
            "voice_id": voice_id,
            "format": format,
            "stream": stream,
            "text": text
        },
        stream=stream
    )

    output_file = f"output.{format}"
    with open(output_file, "wb") as f:
        if stream:
            for chunk in response.iter_content():
                f.write(chunk)
        else:
            f.write(response.content)

    return output_file

# Example usage
voices = list_voices()
print(voices)

audio_file = generate_speech(
    "お客様の声を大切にしています。",
    voice_id="e3362c0a-7677-4cd8-b122-91fb093305c9"
)

const API_URL = 'https://api.shisa.ai';
const API_KEY = 'YOUR_API_KEY';
const headers = {
  'Authorization': `Bearer ${API_KEY}`,
  'Content-Type': 'application/json',
};

// List available voices
const listVoices = async () => {
  const response = await fetch(`${API_URL}/tts/voices`, { headers });
  return response.json();
};

// Generate speech
const generateSpeech = async (text, voiceId = 'e3362c0a-7677-4cd8-b122-91fb093305c9', format = 'mp3') => {
  const response = await fetch(`${API_URL}/tts`, {
    method: 'POST',
    headers,
    body: JSON.stringify({
      voice_id: voiceId,
      format,
      stream: true,
      text,
    }),
  });

  // Handle streaming response
  const reader = response.body.getReader();
  const chunks = [];

  while (true) {
    const { done, value } = await reader.read();
    if (done) break;
    chunks.push(value);
  }

  // Combine chunks and create audio blob
  const blob = new Blob(chunks, { type: `audio/${format}` });
  const url = URL.createObjectURL(blob);

  // Play audio
  const audio = new Audio(url);
  audio.play();
};

// Example usage
const voices = await listVoices();
console.log(voices);

await generateSpeech('ようこそ、Shisa Talkへ。', 'e3362c0a-7677-4cd8-b122-91fb093305c9');