Skip to main content

Generate Audio

For this example, we will use the prebuilt voice Ember with UUID 55592656 and the prompt Speak in an excited, upbeat tone.

If you need to find the UUID for a different voice, refer to the Get All Voices documentation. To learn more about the full range of Text to Speech API options, check out our comprehensive Generating Audio with Text to Speech API Guide.

Remember to replace YOUR_API_TOKEN with your actual API token.

API Request:​

curl --request POST "https://f.cluster.resemble.ai/synthesize"
  -H "Authorization: Bearer YOUR_API_TOKEN"
  -H "Content-Type: application/json"
  -H "Accept-Encoding: gzip"
  --data '{
    "voice_uuid": "55592656",
    "data": "<speak prompt=\"Speak in an excited, upbeat tone\">Hello from Resemble!</speak>",
    "sample_rate": 48000,
    "output_format": "wav"
  }'

API Response:​

{
  "audio_content": <base64 encoded string of the raw audio bytes>,
  "audio_timestamps": {
    "graph_chars": string[],
    "graph_times": float[][],
    "phon_chars": string[],
    "phon-times": float[][],
  },
  "duration": float,
  "issues": string[],
  "output_format": string,
  "sample_rate": float,
  "success": boolean,
  "synth_duration": float,
  "title": string|null
}

All Done!​

You have now successfully generated audio using a voice prompt. The prompt allows you to control the emotional tone and speaking style of the generated audio. Here are some next steps you can explore:

  • Try different prompts to achieve various speaking styles and emotions
  • Create your own custom voice using Voice Design
  • Learn about more advanced Text to Speech features in our API documentation

For any questions or issues, don't hesitate to reach out to our support team.