tts-cache-router docs

LiveKit Agents

Smallest AI with LiveKit

Smallest AI in a LiveKit agent: through our plugin, or through LiveKit's Smallest AI plugin with changed URLs.

View as Markdown

With our plugin#

Smallest AI’s Lightning voices with the settings of LiveKit’s Smallest AI plugin. TTS’s sample_rate is 8000, 16000, 24000 or 44100.

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.SmallestAI(        model="lightning_v3.1_pro",        voice_id="meher",        language="en",    ),)

Pass tts to AgentSession(tts=tts). Set TTS_CACHE_ROUTER_API_KEY in the agent’s environment, and store your Smallest AI key under Provider keys. TTS’s own arguments are on the plugin’s page.

tcr.SmallestAI(...)#

modelstrDefault "lightning_v3.1_pro"
"lightning_v3.1_pro" or "lightning_v3.1".
voice_idstr | NoneDefault None
A Smallest AI voice of model: each model has its own voices, and Smallest AI refuses another model’s. A cloned voice works with the model it was cloned for. None picks meher for lightning_v3.1_pro and sophia for lightning_v3.1, as LiveKit’s plugin does.
languagestrDefault "en"
The language of the text, e.g. en or hi, or auto for Smallest AI to detect it. The languages differ by model.
speedfloatDefault 1.0
Speaking rate, 0.5–2.0.

Every accepted value, and the languages per model: Models and options.

Changing settings#

Replies that start afterwards use the new settings:

Python
tts.update_options(language="hi", speed=1.1)

With LiveKit's Smallest AI plugin#

Keep livekit-plugins-smallestai and point it at the router: your router API key in place of your Smallest AI key, and the router’s address.

pip install livekit-plugins-smallestai
agent.py
import osfrom livekit.plugins import smallestaitts = smallestai.TTS(    model="lightning_v3.1_pro",    voice_id="meher",    language="en",    api_key=os.environ["TTS_CACHE_ROUTER_API_KEY"],    base_url="https://api.ttscacherouter.dev/smallestai/waves/v1",    ws_url="wss://api.ttscacherouter.dev/smallestai/waves/v1/tts/live",)

Set both URLs: ws_url for streaming, as an agent speaks, and base_url for synthesize().

The router splits the reply into sentences and synthesizes each on its own: a sentence’s audio starts once the sentence is complete, and each sentence is a take of its own rather than a continuation of the one before. use_continuations, max_buffer_delay_ms and max_buffer_flush_ms change nothing, and word_timestamps=True gets no word timings. The other differences from Smallest AI’s own messages are on Smallest AI API drop-in.

Requests, responses and errors keep Smallest AI’s own shape; the endpoints are on Smallest AI 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 Smallest AI billed in TTSMetrics (cache hits count zero), and switches provider with update_options.
  • Smallest AI’s plugin is the smallest change to an agent that already uses it. Its metrics count every character, cached or not; Usage has the real split.