https://livekit.io logo
Join Slack
Powered by
Does livekit provides the STT plugin for elevenlab...
# ask-ai
r
Does livekit provides the STT plugin for elevenlabs ?
t
Thanks for reaching out, pritesh. I'm an AI assistant and I'm here to help. Give me a moment while I research this topic.
I'm happy to share that LiveKit offers a Speech-to-Text (STT) plugin specifically for ElevenLabs! This plugin makes it easy to bring ElevenLabs' powerful speech recognition right into the LiveKit Agents framework, allowing you to transcribe audio buffers asynchronously. Here are some helpful features to know about: • You can transcribe audio into text, with support for language codes and even tagging special audio events like laughter or footsteps. • You'll need an ElevenLabs API key, which you can provide directly or set up using the 
ELEVEN_API_KEY
environment variable. • The audio is sent in WAV format to the ElevenLabs API endpoint, using their 
scribe_v1
model. • Keep in mind, transcription works on complete audio buffers — streaming input isn’t supported yet. • This plugin is available in the Python SDK and can be easily installed via PyPI using 
pip install "livekit-agents[elevenlabs]~1.2"
. If you’d like to dive deeper, feel free to explore the plugin repository or check out the Node.js version. I’m here if you have any questions along the way! Sources: ElevenLabs TTS integration guide | LiveKit Docs | Agents Core Architecture | livekit/livekit_composite | DeepWiki | livekit-plugins/livekit-plugins-elevenlabs/livekit/plugins/elevenlabs/py.ty...
r
Can you give sample python snippet for hebrew language ?
t
Thank you for reaching out! I wanted to share some information about the ElevenLabs STT plugin in LiveKit. Currently, it doesn’t explicitly confirm support for Hebrew language transcription. While you can set a 
language_code
parameter, Hebrew (
"he"
) isn’t officially documented as supported for the ElevenLabs STT model. Here’s a Python snippet to show how you might set the language code, but please keep in mind that Hebrew may not work reliably:
Copy code
from livekit.plugins import elevenlabs
import os

# Ensure your ElevenLabs API key is set
os.environ["ELEVEN_API_KEY"] = "your_api_key_here"

# Initialize the STT with attempted Hebrew language code
stt_plugin = elevenlabs.STT(language_code="he")

# Note: Hebrew language support for STT is not confirmed.
# This may default to English or fail depending on ElevenLabs API behavior.
If Hebrew transcription is important for your project, I’d recommend trying the Cartesia STT plugin, which explicitly supports Hebrew. Also, checking the latest ElevenLabs API documentation might give you the most up-to-date info on supported languages. I hope this helps, and please feel free to ask if you have any more questions! Sources: pipeline-tts/elevenlabs_tts.py | ElevenLabs TTS integration guide | LiveKit Docs | livekit-plugins/livekit-plugins-cartesia/livekit/plugins/cartesia/stt.py
3 Views
Open in Slack
PreviousNext
Powered by