livekit-plugins-shunyalabs
Shunyalabs STT and TTS plugin for LiveKit Agents.
Provides STT (speech-to-text) and TTS (text-to-speech) classes that integrate with LiveKit's agent framework, backed by the Shunyalabs Python SDK.
Installation
pip install livekit-plugins-shunyalabs
Authentication
Set your API key as an environment variable:
export SHUNYALABS_API_KEY="your-api-key"
Or pass it directly:
stt = shunyalabs.STT(api_key="your-api-key")
tts = shunyalabs.TTS(api_key="your-api-key")
Quick Start
from livekit.agents import AgentSession
from livekit.plugins import shunyalabs, silero
session = AgentSession(
stt=shunyalabs.STT(language="en"),
tts=shunyalabs.TTS(speaker="Rajesh", style="<Neutral>"),
vad=silero.VAD.load(),
)
STT (Speech-to-Text)
shunyalabs.STT
| Parameter | Type | Default | Description |
|---|---|---|---|
api_key |
str |
None |
API key. Falls back to SHUNYALABS_API_KEY env var. |
language |
str |
"auto" |
BCP-47 language code or "auto" for auto-detection. |
api_url |
str |
https://asr.shunyalabs.ai |
REST batch endpoint base URL. |
ws_url |
str |
wss://asr.shunyalabs.ai/ws |
WebSocket streaming endpoint URL. |
Capabilities
| Capability | Supported |
|---|---|
| Streaming (real-time) | Yes |
| Interim results | Yes |
| Offline/batch recognition | Yes |
Streaming STT
Real-time transcription over WebSocket. Audio frames from LiveKit are forwarded to the Shunyalabs ASR gateway; transcription events are pushed back as SpeechEvents.
from livekit.agents import AgentSession
from livekit.plugins import shunyalabs, silero
session = AgentSession(
stt=shunyalabs.STT(language="en"),
vad=silero.VAD.load(),
)
@session.on("user_speech_committed")
def on_speech(ev):
print(f"User said: {ev.transcript}")
Event mapping:
| Shunyalabs Event | LiveKit SpeechEventType |
|---|---|
PARTIAL |
INTERIM_TRANSCRIPT |
FINAL_SEGMENT |
FINAL_TRANSCRIPT + END_OF_SPEECH |
FINAL |
FINAL_TRANSCRIPT + RECOGNITION_USAGE |
Batch STT
Single-shot transcription of an audio buffer. Uses POST /v1/audio/transcriptions via the SDK's AsyncBatchASR.
from livekit.plugins import shunyalabs
stt = shunyalabs.STT(language="en")
# In an agent context:
event = await stt.recognize(audio_buffer)
print(event.alternatives[0].text)
TTS (Text-to-Speech)
shunyalabs.TTS
| Parameter | Type | Default | Description |
|---|---|---|---|
api_key |
str |
None |
API key. Falls back to SHUNYALABS_API_KEY env var. |
api_url |
str |
https://tts.shunyalabs.ai |
HTTP batch endpoint base URL. |
ws_url |
str |
wss://tts.shunyalabs.ai/ws |
WebSocket streaming endpoint URL. |
model |
str |
"zero-indic" |
TTS model name. |
voice |
str |
"Rajesh" |
Voice name for the API. |
speaker |
str |
"Rajesh" |
Speaker name prefix for text formatting. |
style |
str |
"<Neutral>" |
Emotion style tag. See Style Tags. |
language |
str |
"en" |
Language code for transliteration. |
sample_rate |
int |
16000 |
Output audio sample rate in Hz. |
output_format |
str |
"pcm" |
Audio format ("pcm", "wav", "mp3", "ogg_opus", "flac"). |
speed |
float |
1.0 |
Speaking speed multiplier (0.25–4.0). |
Style Tags
| Tag | Description |
|---|---|
<Neutral> |
Neutral tone |
<Happy> |
Happy/cheerful |
<Sad> |
Sad/melancholic |
<Angry> |
Angry/intense |
<Fearful> |
Fearful/anxious |
<Surprised> |
Surprised/excited |
<Disgust> |
Disgusted |
<News> |
News anchor style |
<Conversational> |
Casual conversational |
<Narrative> |
Storytelling/narration |
<Enthusiastic> |
Enthusiastic/energetic |
Text Formatting
The plugin automatically formats text as "<Style> text" before sending to the API. For example:
tts = shunyalabs.TTS(speaker="Rajesh", style="<Happy>")
# Input: "Welcome to our platform"
# Sent: "<Happy> Welcome to our platform"
Streaming TTS
Token-by-token streaming. Collects text tokens, then synthesizes on flush via WebSocket streaming.
from livekit.agents import AgentSession
from livekit.plugins import shunyalabs
session = AgentSession(
tts=shunyalabs.TTS(
speaker="Nisha",
style="<Conversational>",
model="zero-indic",
voice="Nisha",
),
)
Chunked (Batch) TTS
Single text → audio synthesis via HTTP batch API.
from livekit.plugins import shunyalabs
tts = shunyalabs.TTS(speaker="Varun", voice="Varun")
stream = tts.synthesize("Hello, how can I help you today?")
Full Agent Example
import asyncio
from livekit import api
from livekit.agents import AgentSession, Agent, RoomInputOptions
from livekit.plugins import shunyalabs, silero
class MyAgent(Agent):
def __init__(self):
super().__init__(
instructions="You are a helpful voice assistant.",
)
async def entrypoint(ctx):
session = AgentSession(
stt=shunyalabs.STT(language="auto"),
tts=shunyalabs.TTS(
model="zero-indic",
voice="Rajesh",
speaker="Rajesh",
style="<Conversational>",
),
vad=silero.VAD.load(),
)
await session.start(
agent=MyAgent(),
room=ctx.room,
room_input_options=RoomInputOptions(),
)
Multilingual Example
# Hindi speaker
tts_hindi = shunyalabs.TTS(
speaker="Rajesh",
voice="Rajesh",
language="hi",
style="<Neutral>",
)
# English speaker
tts_english = shunyalabs.TTS(
speaker="Varun",
voice="Varun",
language="en",
style="<Conversational>",
)
License
Metadata
Release files for livekit-plugins-shunyalabs 1.0.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| livekit_plugins_shunyalabs-1.0.1.tar.gz | 11.6 kB | Without provenance | Details for livekit_plugins_shunyalabs-1.0.1.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| livekit_plugins_shunyalabs-1.0.1-py3-none-any.whl | Python 3 | none | any | Details for livekit_plugins_shunyalabs-1.0.1-py3-none-any.whl |
Total release size: 23.5 kB
Release files / livekit_plugins_shunyalabs-1.0.1.tar.gz
| Download URL | livekit_plugins_shunyalabs-1.0.1.tar.gz |
|---|---|
| Size | 11.6 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
38f9c0e538b828c2643def70c3d6870a5982ab538e6255a417a55ea57cf35ee9
|
|
BLAKE2b-256 checksum How to use checksums |
07c2d020c8efe7002230847bf3a1d6545f9b49a5e3486a360e802432f5158bd6
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.10.12
|
Release files / livekit_plugins_shunyalabs-1.0.1-py3-none-any.whl
| Download URL | livekit_plugins_shunyalabs-1.0.1-py3-none-any.whl |
|---|---|
| Size | 11.9 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
8b6ba387ab9e44b55213833340eaac6559e49fed10b8ce49178af8f7bb450753
|
|
BLAKE2b-256 checksum How to use checksums |
91dfc12538103e1298ccdfe2120f1cf2fcca78ac99fcc75e5bd2f95bef0ffdfa
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.10.12
|
Security for livekit-plugins-shunyalabs 1.0.1
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.