lyra on Coda, Rime’s flagship model) — the fastest way to hear Rime. Choose a speaker and modelId from list_voices and get_voice_details.
API key: Required — see Authentication. Samples consume credits like any other API request, so keep sample text short.
Parameters
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
text | string | No | A short demo line | Text to synthesize (max 2,000 characters) |
speaker | string | No | lyra | Voice name from list_voices |
modelId | string | No | coda | Model ID: coda (flagship), mistv3, or arcana |
language | string | No | — | Sent as lang only if provided (e.g. eng, the value from get_voice_details). Omit to let Rime infer the language from the speaker |
include_audio | boolean | No | false | Also return the audio as a standard MCP audio content block (base64), for hosts that play audio natively. Adds the audio to the model’s context |
Returns
Audio is delivered three ways so it plays regardless of the host — an inline player in UI hosts, a short-lived play URL (structuredContent.audioUrl) for terminal hosts, and an optional audio content block. See Playing audio.
Example
Ask your assistant:Related
- Playing audio — how samples reach your speakers in each host
- Models — compare Coda, Mist v3, and Arcana
- Streaming APIs — production synthesis