tts-cache-router docs

LiveKit Agents

Deepgram with LiveKit

Deepgram's Aura and Flux in a LiveKit agent: through our plugin, or through LiveKit's Deepgram plugin with a changed URL.

With our plugin#

Deepgram’s Aura and Flux with the settings of LiveKit’s Deepgram plugin (TTS and TTSv2). Deepgram’s model id is the model and the voice joined: model="aura-2" and voice="thalia-en" is aura-2-thalia-en. With Aura, the first sentence of a reply after a pause of about five seconds or more takes about 0.7–1.2 s longer to start than with LiveKit’s plugin; sentences from the cache, and Flux, are unaffected.

pip install livekit-plugins-tts-cache-router
agent.py
from livekit.plugins import tts_cache_router as tcr# The API key comes from TTS_CACHE_ROUTER_API_KEY.tts = tcr.TTS(    provider=tcr.Deepgram(        model="aura-2",        voice="thalia-en",    ),)

Pass tts to AgentSession(tts=tts). Set TTS_CACHE_ROUTER_API_KEY in the agent’s environment, and store your Deepgram key under Provider keys. The constructor of TTS itself is on the plugin’s page.

tcr.Deepgram(...)#

modelstrDefault "aura-2"
aura-2, aura-1 or flux.
voicestrDefault "andromeda-en"
The voice with its language, e.g. thalia-en (Aura-2), asteria-en (Aura-1) or alexis-en (Flux).
speedfloat | NoneDefault None
Speaking rate, 0.7–1.5, aura-2 only. None leaves it to Deepgram.
mip_opt_outboolDefault False
Opt out of Deepgram's Model Improvement Program.

Every value the router accepts, and the languages per model, are in Models and options.

Changing settings#

Replies that start afterwards use the new settings:

Python
tts.update_options(voice="andromeda-en")

With LiveKit's Deepgram plugin#

Keep livekit-plugins-deepgram and point it at the router: your router API key in place of your Deepgram key, and the router’s address. Nothing else changes.

pip install livekit-plugins-deepgram
agent.py
import osfrom livekit.plugins import deepgramtts = deepgram.TTS(    model="aura-2-thalia-en",    api_key=os.environ["TTS_CACHE_ROUTER_API_KEY"],    base_url="https://api.ttscacherouter.dev/deepgram/v1/speak",)

For Flux, use deepgram.TTSv2(model="flux-alexis-en", …) with base_url ending in /deepgram/v2/speak. The plugin streams your agent’s reply word by word; the router splits it into sentences and caches each one, with a few differences from Deepgram’s own messages.

Requests, responses and errors keep Deepgram’s own shape. The endpoints behind it are described in Deepgram API drop-in.

Which to choose#

Both use your org's cache and your stored provider key, and sound the same.

  • Our plugin reports only the characters Deepgram billed in LiveKit’s TTSMetrics (cache hits count zero), and lets you switch provider with update_options.
  • Deepgram’s plugin is the smallest change to an agent that already uses it. Its metrics count every character, cached or not; the dashboard’s Usage page has the real split.