Prediction

const input = {
  bitrate: 128000,
  channel: "mono",
  emotion: "angry",
  english_normalization: true,
  language_boost: "English",
  pitch: 0,
  sample_rate: 32000,
  speed: 1,
  text: "Speech-02-series is a Text-to-Audio and voice cloning technology that offers voice synthesis, emotional expression, and multilingual capabilities.\n\nThe HD version is optimized for high-fidelity applications like voiceovers and audiobooks. While the turbo one is designed for real-time applications with low latency.\n\nWhen using this model on Replicate, each character represents 1 token.",
  voice_id: "Deep_Voice_Man",
  volume: 1
};

const output = await replicate.run("minimax/speech-02-turbo", { input });

// To access the file URL:
console.log(output.url()); //=> "http://example.com"

// To write the file to disk:
fs.writeFile("my-image.png", output);

output = replicate.run(
    "minimax/speech-02-turbo",
    input={
        "bitrate": 128000,
        "channel": "mono",
        "emotion": "angry",
        "english_normalization": True,
        "language_boost": "English",
        "pitch": 0,
        "sample_rate": 32000,
        "speed": 1,
        "text": "Speech-02-series is a Text-to-Audio and voice cloning technology that offers voice synthesis, emotional expression, and multilingual capabilities.\n\nThe HD version is optimized for high-fidelity applications like voiceovers and audiobooks. While the turbo one is designed for real-time applications with low latency.\n\nWhen using this model on Replicate, each character represents 1 token.",
        "voice_id": "Deep_Voice_Man",
        "volume": 1
    }
)

# To access the file URL:
print(output.url())
#=> "http://example.com"

# To write the file to disk:
with open("my-image.png", "wb") as file:
    file.write(output.read())

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "input": {
      "bitrate": 128000,
      "channel": "mono",
      "emotion": "angry",
      "english_normalization": true,
      "language_boost": "English",
      "pitch": 0,
      "sample_rate": 32000,
      "speed": 1,
      "text": "Speech-02-series is a Text-to-Audio and voice cloning technology that offers voice synthesis, emotional expression, and multilingual capabilities.\\n\\nThe HD version is optimized for high-fidelity applications like voiceovers and audiobooks. While the turbo one is designed for real-time applications with low latency.\\n\\nWhen using this model on Replicate, each character represents 1 token.",
      "voice_id": "Deep_Voice_Man",
      "volume": 1
    }
  }' \
  https://api.replicate.com/v1/models/minimax/speech-02-turbo/predictions