> ## Documentation Index
> Fetch the complete documentation index at: https://docs.sabi-tts-app.dev.neuralace.co/llms.txt
> Use this file to discover all available pages before exploring further.

# Introduction

> Capella is Sabi's expressive text-to-speech voice model, served through an OpenAI-compatible API.

## What is Capella?

Capella is Sabi's fine-tuned text-to-speech voice model, built for natural, expressive
English speech. It supports inline **audio tags** — laughs, sighs, breaths, pauses, and
per-sentence emotional styles — so generated speech sounds like a performance, not a readout.

Capella is served through two front doors:

<CardGroup cols={2}>
  <Card title="HTTP API" icon="globe" href="/api-reference/speech">
    Drop-in OpenAI-compatible `POST /v1/audio/speech`. Point the OpenAI SDK at our base URL
    and it just works.
  </Card>

  <Card title="Streaming WebSocket" icon="bolt" href="/api-reference/streaming">
    Low-latency, sentence-by-sentence audio frames for conversational and real-time apps.
  </Card>

  <Card title="Capella reference" icon="microphone" href="/capella/capella">
    Configuration parameters, environment variables, and usage examples.
  </Card>

  <Card title="Audio tags" icon="wand-magic-sparkles" href="/capella/audio-tags">
    The full vocabulary of event tags and style wraps for expressive delivery.
  </Card>
</CardGroup>

## Capabilities

* **Expressive delivery** — inline event tags (`<|laugh|>`, `<|sigh|>`, `<|pause|>` …) and
  sentence-level style wraps (excited, whispers, sarcastic, accents, …).
* **OpenAI compatibility** — use the official OpenAI Python or Node SDK unchanged; only the
  base URL and API key differ.
* **Real-time streaming** — a WebSocket protocol that returns one audio frame per sentence
  as it is synthesized.
* **Multiple output formats** — `wav`, `mp3`, `pcm`, `opus`, and `flac`.
* **Per-request observability** — every HTTP response carries `x-upstream-ms` and
  `x-gateway-ms` timing headers.

## Use cases

* Conversational agents and voice assistants that need low first-audio latency.
* Content production: narration, voiceovers, and character work with emotional range.
* Product experiences that read dynamic text aloud with natural pacing.