Rime

Rime is a text-to-speech plugin. It converts the agent’s text responses into low-latency, natural-sounding speech.

Setup

Set your Rime API key in the worker environment. Generate a key from the Rime site:

export RIME_API_KEY=<key>

Import the plugin and pass it to the pipeline’s tts slot.

Python

from zrt.plugins import RimeTTS

tts = RimeTTS()

# Pipeline(tts=tts, ...)

Parameter	Type	Default	Description
`api_key`	`str \| None`	`None`	Rime API key. Falls back to the `RIME_API_KEY` environment variable when unset.
`speaker`	`str`	`"river"`	Voice/speaker identifier to use for synthesis. Available speakers depend on the chosen `model_id`; example cross-model voices include `"astra"`, `"luna"`, `"celeste"`, `"masonry"`, `"albion"`, and `"cove"`.
`model_id`	`str`	`"mist"`	Rime model identifier. Known options: `"mist"` / `"mistv2"` (fast, streaming-optimised conversational model), `"coda"` (Rime’s most realistic conversational voices), `"v1"` (legacy model).
`sampling_rate`	`int`	`24000`	Output audio sample rate in Hz.

Synthesized audio is streamed back to the caller after the LLM produces a response.