# Kosmik: MOSS-TTS-Nano

Canonical model ID: `kosmik/tts-moss-nano`

Multilingual speech synthesis with built-in voices, including Czech. WAV output; speed must be 1. Custom reference voices are not supported by this endpoint.

## Runtime metadata

This table is generated from public model metadata. Readiness and capacity are refreshed from `GET /v1/models` on page load.

| Property | Value |
|---|---|
| Kind | `audio-speech` |
| Input | text |
| Output | audio |
| Context | Not token-based |
| Maximum output | Endpoint-specific |
| Supported endpoints | `/v1/audio/speech` |
| Capabilities | Endpoint-specific |
| Pricing | $4.00 per 1M characters |

## Speech limits

Maximum input: 1,000 characters per request.

Default voice: `Junhao`.

## License and usage

Review the [speech model licenses and usage terms](/docs/security/speech-model-licenses/) before calling this model.

## Voices

| Voice ID | Language | Name |
|---|---|---|
| `Junhao` |  | Junhao |
| `Zhiming` |  | Zhiming |
| `Weiguo` |  | Weiguo |
| `Xiaoyu` |  | Xiaoyu |
| `Yuewen` |  | Yuewen |
| `Lingyu` |  | Lingyu |
| `Trump` |  | Trump |
| `Ava` |  | Ava |
| `Bella` |  | Bella |
| `Adam` |  | Adam |
| `Nathan` |  | Nathan |
| `Soyo` |  | Soyo |
| `Saki` |  | Saki |
| `Mortis` |  | Mortis |
| `Umiri` |  | Umiri |
| `Mei` |  | Mei |
| `Anon` |  | Anon |
| `Arisa` |  | Arisa |

## Use this model

Copy the canonical ID into the `model` field. Check the endpoint guide before using optional capabilities.