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

# Rime TTS

> Arcana and Mist model families via Rime's HTTP endpoint.

# Rime TTS

`RimeTTS` targets the [Rime HTTP endpoint](https://rime.ai/docs). Both Arcana (high fidelity) and Mist (low latency) model families are supported. The provider requests `audio/pcm` and yields raw PCM\_S16LE chunks at the configured sample rate.

## Install

```bash theme={null}
npm install getpatter
```

No vendor SDK is required — `RimeTTS` uses the platform `fetch`, so it works on Node 18+.

## Usage

```typescript theme={null}
import { RimeTTS } from "getpatter";

const tts = new RimeTTS();                                            // reads RIME_API_KEY
const tts2 = new RimeTTS({ model: "arcana", speaker: "astra" });
```

In an agent:

```typescript theme={null}
// npx tsx example.ts
import { Patter, Twilio, DeepgramSTT, RimeTTS } from "getpatter";

const phone = new Patter({ carrier: new Twilio(), phoneNumber: "+15550001234" });

const agent = phone.agent({
  stt: new DeepgramSTT(),                             // DEEPGRAM_API_KEY from env
  tts: new RimeTTS({ model: "arcana", speaker: "astra" }),  // RIME_API_KEY from env
  systemPrompt: "You are a helpful assistant.",
});

await phone.serve({ agent });
```

Mist v2 — low-latency, streaming-friendly:

```typescript theme={null}
const fast = new RimeTTS({
  model: "mistv2",
  speaker: "cove",
  speedAlpha: 1.1,
  reduceLatency: true,
});
```

## Options (selection)

| Option                                                                            | Default              | Notes                                          |
| --------------------------------------------------------------------------------- | -------------------- | ---------------------------------------------- |
| `apiKey`                                                                          | —                    | Reads from `RIME_API_KEY` when omitted.        |
| `model`                                                                           | `"arcana"`           | `"arcana"` or any `mist*` model.               |
| `speaker`                                                                         | `"astra"` / `"cove"` | Default depends on model.                      |
| `lang`                                                                            | `"eng"`              | Rime language code.                            |
| `sampleRate`                                                                      | `16000`              | Hz.                                            |
| `temperature`, `topP`, `maxTokens`, `repetitionPenalty`                           | —                    | Arcana only.                                   |
| `speedAlpha`, `reduceLatency`, `pauseBetweenBrackets`, `phonemizeBetweenBrackets` | —                    | Mist only.                                     |
| `baseUrl`                                                                         | Rime `/v1/rime-tts`  | Override for proxying or self-hosted gateways. |