Skip to main content

Rime AI TTS

The Rime AI TTS provider enables your agent to use Rime AI's high-quality text-to-speech models for generating natural-sounding voice output.

Installation​

Install the Rime AI-enabled VideoSDK Agents package:

pip install "videosdk-plugins-rime"

Importing​

from videosdk.plugins.Rime import RimeTTS

Authentication​

The Rime plugin requires an Rime API key.

Set RIME_API_KEY in your .env file.

Example Usage​

from videosdk.plugins.Rime import RimeTTS
from videosdk.agents import CascadingPipeline

# Initialize the Rime AI TTS model
tts = RimeTTS(
speaker="river",
model_id="mist",
lang="eng",
speed_alpha=1.0
)

# Add tts to cascading pipeline
pipeline = CascadingPipeline(tts=tts)
note

When using .env file for credentials, don't pass them as arguments to model instances or context objects. The SDK automatically reads environment variables, so omit api_key and other credential parameters from your code.

Configuration Options​

  • speaker: (str) Voice ID to use (default: "river"). Must match the model's available speakers.
  • model_id: (str) Rime model identifier (default: "mist"). Supported: "mist", "mistv2".
  • lang: (str) Language code for the voice (default: "eng").
  • speed_alpha: (float) Controls speaking rate (1.0 is normal speed).
  • reduce_latency: (bool) Whether to minimize streaming delay (default: False).
  • pause_between_brackets: (bool) Insert pauses around bracketed text (default: False).
  • phonemize_between_brackets: (bool) Use phonemes for bracketed text (default: False).
  • inline_speed_alpha: (str) Optional per-word speed override (e.g., "1.2,1.0,0.8").
  • api_key: (str) Rime API key. Can also be set via the RIME_API_KEY environment variable.

Additional Resources​

The following resources provide more information about using Rime with VideoSDK Agents SDK.

Got a Question? Ask us on discord