> ## Documentation Index
> Fetch the complete documentation index at: https://docs.breezeblue.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Output formats

> Audio codec, sample rate, and bitrate options for text to speech.

The `output_format` query parameter selects the audio encoding. Non-streaming text to speech accepts `mp3`, `wav`, `flac`, `pcm`, `aac`, and `opus`. Streaming supports `mp3` and `pcm`.

## Supported encodings

| Value  | Format  | Notes                               |
| ------ | ------- | ----------------------------------- |
| `mp3`  | MP3     | Default. Best for general playback. |
| `wav`  | WAV     | Uncompressed, lossless.             |
| `flac` | FLAC    | Lossless compression.               |
| `pcm`  | Raw PCM | Linear PCM for audio pipelines.     |
| `aac`  | AAC     | Efficient lossy codec.              |
| `opus` | Opus    | Non-streaming only.                 |

## Choosing a format

* **End-user playback in a browser or app**: prefer `mp3`.
* **Real-time applications**: use the streaming endpoint with `mp3` or `pcm`.
* **Archival or post-processing**: use `wav` or `flac` for lossless output.

## Use formats with

<Columns cols={2}>
  <Card title="SDK quickstart" icon="rocket" href="/quickstart">
    Generate and save your first MP3 with the Python or TypeScript SDK.
  </Card>

  <Card title="Text to speech" icon="mic" href="/guides/text-to-speech">
    Pass `output_format` on sync, async, and streaming generation requests.
  </Card>

  <Card title="Streaming" icon="radio" href="/concepts/streaming">
    Use streaming-compatible formats for lower-latency playback.
  </Card>

  <Card title="CLI text to speech" icon="terminal" href="/cli/reference/tts">
    Save generated audio from the command line while prototyping voices and formats.
  </Card>
</Columns>