livekit-plugins-gladia

What it is and what it does

This package bridges Gladia's speech-to-text service into the LiveKit Agents framework, allowing you to add real-time transcription to LiveKit-based applications. It wraps Gladia's API with a streaming interface that handles audio input and returns transcriptions, with support for interim (partial) results as speech is being recognized.

The plugin exposes Gladia's feature set—multi-language recognition, code-switching between languages during a single utterance, voice activity detection with energy filtering, and optional real-time translation—through a simple initialization and update interface. You configure it with language preferences, audio parameters (sample rate, bit depth, encoding), and optional translation targets, then pass it to a LiveKit Agent as its STT provider. It depends on aiohttp for HTTP communication, livekit-agents for the framework integration, and numpy for audio processing.

Use it for:

• Build a multilingual LiveKit agent that automatically recognizes and transcribes speech in multiple languages without manual language selection.
• Add real-time translation to a LiveKit video call, transcribing speech and translating it to a target language on the fly.
• Implement voice activity detection in a LiveKit agent to filter background noise and only process actual speech.
• Create a custom vocabulary for domain-specific terms (e.g., product names, proper nouns) to improve transcription accuracy in specialized applications.
• Use interim results to show partial transcriptions to users as they speak, improving perceived responsiveness in real-time communication.

Worth the install?

AI-flagged interpretation of the facts on this page — verify before relying

Integrates Gladia's speech-to-text API with LiveKit Agents, enabling streaming transcription with multi-language support, code-switching, interim results, and optional real-time translation.

Yes. The package is actively maintained, has no known vulnerabilities, installs with low friction, and is permissively licensed. Install it if you are building a LiveKit Agents application and need Gladia's speech-to-text capabilities; it is the intended integration point for that use case. Verify that Gladia's pricing and language support meet your requirements before committing.

Install

livekit-plugins-gladia on PyPI

pip install livekit-plugins-gladia

uv add livekit-plugins-gladia

poetry add livekit-plugins-gladia

Installing livekit-plugins-gladia

Before you install

Low install friction; pure Python wheel with three lightweight runtime dependencies (aiohttp, livekit-agents, numpy). Active maintenance with a recent release.

License in practice

Apache-2.0 permissive license allows commercial and private use with minimal restrictions; suitable for most projects.

Quickstart

pip install livekit-plugins-gladia

from livekit.plugins.gladia.stt import STT as GladiaSTT

stt = GladiaSTT(
    api_key="your-api-key-here",
    languages=["en"],
    interim_results=True
)

Requires a Gladia API key, set via GLADIA_API_KEY environment variable or passed directly. Requires Python >=3.10.0.

Verify before relying

• Actual latency and throughput characteristics of streaming transcription in production.
• Supported languages and code-switching language pairs beyond the documented examples.
• Pricing and rate limits for the Gladia API integration.

Package facts

Evidence: livekit_plugins_gladia-1.6.10-py3-none-any.whl

Keywords: ai, audio, gladia, livekit, realtime, speech-to-text, video, voice

Tags

More Artificial Intelligence packages

Further reading