> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.resemble.ai/guides/prompt-generation/generate-audio/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.resemble.ai/_mcp/server.

# Generate Audio

This example uses the prebuilt voice **Ember** (`voice_uuid = 55592656`) and the prompt `Speak in an excited, upbeat tone`.

```bash
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"
  }'
```

Response:

```json
{
  "audio_content": "... base64 ...",
  "audio_timestamps": {
    "graph_chars": [],
    "graph_times": [],
    "phon_chars": [],
    "phon_times": []
  },
  "duration": 1.84,
  "output_format": "wav",
  "sample_rate": 48000,
  "success": true
}
```

Decode `audio_content` or download `audio_src` (if present) to listen.

## Next Steps

* Try alternative prompts to explore different deliveries.
* Review the [Text-to-Speech reference](/voice-generation/text-to-speech/synchronous) for additional parameters.