Skip to main content
building on livekit agents? use livekit-plugins-rumik-ai, our official livekit TTS plugin. it drops rumik straight into an AgentSession with streaming audio and interruption handling already wired up. 
pip install livekit-plugins-rumik-ai
set your key from the dashboard: 
export RUMIK_API_KEY="rk_live_•••••••••"

​
add it to an agent

the TTS class plugs into a livekit AgentSession next to your STT and LLM: 
from livekit.agents import AgentSession
from livekit.plugins import rumik_ai

# muga: expressive, tone-tagged hinglish
session = AgentSession(
    stt=...,   # your speech-to-text plugin
    llm=...,   # your llm plugin
    tts=rumik_ai.TTS(model="muga"),
)
steer mulberry with a natural-language description, or pin a preset speaker: 
# mulberry: description-driven voice
tts = rumik_ai.TTS(
    model="mulberry",
    description="a female 30s hindi voice, warm timbre, conversational pacing, like a podcast host",
)

# or a preset studio voice
tts = rumik_ai.TTS(model="mulberry", speaker="speaker_1", f0_up_key=3)

​
constructor options

argumentapplies tonotes
modelboth"muga" or "mulberry". default "muga".
api_keybothdefaults to the RUMIK_API_KEY environment variable.
base_urlbothdefaults to https://silk-api.rumik.ai.
full_response_aggregationbothbuffer the full reply before synthesis. default True for muga, False for mulberry.
tonemugafallback tone when the input text has no [tone] marker.
descriptionmulberrynatural-language voice description.
speakermulberrypreset voice speaker_1 to speaker_4.
f0_up_keymulberrypitch shift in semitones, -12 to 12.
it also accepts the shared sampling params (temperature, top_p, top_k, repetition_penalty, max_new_tokens).
muga aggregates the full tagged reply before speaking (full_response_aggregation is True by default), so it never tries to synthesize a half-tagged sentence. see prompting muga for why.

​
which model?

  • muga for short, expressive reactions you steer with [tone] tags. see prompting muga.
  • mulberry for low-latency conversational agents you steer with a description. see prompting mulberry.
prefer a full walkthrough? the livekit cookbook builds a working voice agent from scratch. or hand your coding agent the rumik TTS skill so it wires all of this up on the first try.