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

# Voices

> Rime's voice catalog across Coda, Arcana, and Mist — and how to pick a starter voice.

Rime exposes a broad portfolio of production-ready voices across our models. Each voice is designed for real-time conversational performance, with distinct tonal identity, emotional range, and demographic diversity.

## Languages

As of 19 May 2026, Rime supports the following languages:

| Language   | ISO codes    | Notes        |
| :--------- | :----------- | :----------- |
| English    | `eng` / `en` |              |
| Spanish    | `spa` / `es` |              |
| French     | `fra` / `fr` |              |
| Portuguese | `por` / `pt` | Coda, Arcana |
| German     | `ger` / `de` |              |
| Japanese   | `jpn` / `ja` | Coda, Arcana |
| Hebrew     | `heb` / `he` | Arcana only  |

<Tip>For the live voice list, fetch [`/data/voices/all-v2.json`](/api-reference/data/voices-v2) — it updates as new voices ship.</Tip>

## Accessing Voices

* Online: [/api-reference/data/voices](/api-reference/data/voices)
* Via API: [https://users.rime.ai/data/voices/all-v2.json](https://users.rime.ai/data/voices/all-v2.json)

Detailed voice metadata is available:

* Online: [/api-reference/data/voice-details](/api-reference/data/voice-details)
* Via API: [https://users.rime.ai/data/voices/voice\_details.json](https://users.rime.ai/data/voices/voice_details.json)

Use the `speaker` parameter in the TTS API to select a voice:

```json theme={null}
{
  "speaker": "astra",
  "text": "Hello from Rime!",
  "modelId": "coda",
  "language": "en"
}
```

## Starter voices to try

If you're just getting started, these speakers are confirmed to work across the listed models:

| Speaker   | Sounds like                            | Works on                       |
| :-------- | :------------------------------------- | :----------------------------- |
| `astra`   | Female, young adult, American Standard | Coda, Arcana, Mist v3, Mist v2 |
| `luna`    | Female, young adult, American          | Coda, Arcana, Mist v3          |
| `celeste` | Female, young adult, American          | Coda, Arcana                   |
| `masonry` | Male, middle-aged, Southern            | Coda, Arcana                   |
| `albion`  | Male, young adult, English             | Coda, Arcana                   |
| `cove`    | Female, young adult, African American  | Mist v3, Mist v2               |

For the complete catalog, fetch [`/data/voices/voice_details.json`](/api-reference/data/voice-details).

## Coda Voices (Flagship)

Coda is Rime's new flagship model. Its featured voices in the [Rime dashboard](https://app.rime.ai) are organized into four styles. Each style includes both female and male options.

### Professional

| Speaker      | Gender | Age   | Description                                                              |
| :----------- | :----- | :---- | :----------------------------------------------------------------------- |
| `lyra`       | Female | 18–30 | A warm young American voice — bright and lively.                         |
| `clementine` | Female | 30–50 | A warm, lively middle-aged American voice — both polished and energetic. |
| `masonry`    | Male   | 30–50 | A confident, low Southern voice — authoritative without being loud.      |
| `walnut`     | Male   | 18–30 | A fast, confident young Southern voice — authoritative and steady.       |

### Formal

| Speaker    | Gender | Age   | Description                                                             |
| :--------- | :----- | :---- | :---------------------------------------------------------------------- |
| `lintel`   | Female | 18–30 | A warm young American voice — both polished and lively.                 |
| `eyre`     | Female | 18–30 | A warm, friendly American voice — calm and easy to listen to.           |
| `bancroft` | Male   | 60+   | A composed American voice — strong on professional and formal contexts. |
| `marlu`    | Male   | 30–50 | An older Australian voice; low, mature, unhurried.                      |

### Casual

| Speaker   | Gender | Age   | Description                                                   |
| :-------- | :----- | :---- | :------------------------------------------------------------ |
| `hesse`   | Female | 18–30 | A relaxed, easygoing female voice.                            |
| `luna`    | Female | 18–30 | A bright, lively female voice — energetic with a casual core. |
| `beatty`  | Male   | 18–30 | An easygoing, distinctly casual American male voice.          |
| `godfrey` | Male   | 18–30 | An easygoing, lively American male voice — casual at heart.   |

### Energetic

| Speaker   | Gender | Age   | Description                                                        |
| :-------- | :----- | :---- | :----------------------------------------------------------------- |
| `astra`   | Female | 18–30 | Bright, lively Californian — quick and expressive.                 |
| `vespera` | Female | 18–30 | A friendly, lively young Californian voice — bright and adaptable. |
| `parapet` | Male   | 30–50 | A fast, lively Southern voice — energetic and grounded.            |
| `cupola`  | Male   | 30–50 | A confident, energetic American voice — professional with warmth.  |

All voices above are confirmed-working with `modelId: coda`. For the complete catalog including non-English languages, fetch [`/data/voices/voice_details.json`](/api-reference/data/voice-details).

## Arcana v3 Voices

<Tip>Coda is meaningfully better than Arcana across naturalness, prosody, and artifact-free output. For new projects, prefer Coda; for existing Arcana traffic, we recommend migrating to Coda — see [Migrating from Arcana](/docs/introduction#migrating-from-arcana).</Tip>

Arcana v3 is Rime's previous flagship — a multilingual model with 94 expressive voices spanning age groups, regional accents, cultural backgrounds, and energy profiles.

See the [full voice list](/api-reference/data/voices) and [voice details](/api-reference/data/voice-details) for available Arcana speakers.

### The 94 Arcana Flagship Voices

Arcana v3 includes 94 flagship voices across English (US regional, international) plus the other [supported Arcana languages](#languages). See [`/data/voices/voice_details.json`](/api-reference/data/voice-details) for the full catalog with demographics.

## Mist v3 Voices

Mist v3 supports the same popular speaker lineup as Mist v2 with significantly lower TTFA.

See the [full voice list](/api-reference/data/voices) for available Mist v3 speakers.

## Mist v2 Voices

Mist v2 prioritizes clarity, pronunciation accuracy, and high-throughput production. For new projects, prefer Mist v3.

See the [full voice list](/api-reference/data/voices) for available Mist v2 speakers.