Metadata-Version: 2.4
Name: livekit-plugins-reson8
Version: 0.1.1
Summary: Reson8 STT plugin for LiveKit Agents
Project-URL: Homepage, https://github.com/reson8lab/livekit-plugins-reson8
Project-URL: Repository, https://github.com/reson8lab/livekit-plugins-reson8
License-Expression: Apache-2.0
License-File: LICENSE
Keywords: agents,livekit,reson8,speech-to-text,stt
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: Apache Software License
Classifier: Programming Language :: Python :: 3
Classifier: Topic :: Multimedia :: Sound/Audio :: Speech
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Requires-Python: >=3.9
Requires-Dist: httpx>=0.28
Requires-Dist: livekit-agents[codecs]>=1.0
Requires-Dist: websockets>=13.0
Description-Content-Type: text/markdown

# livekit-plugins-reson8

[Reson8](https://reson8.dev) STT plugin for [LiveKit Agents](https://github.com/livekit/agents).

Supports real-time streaming and prerecorded speech-to-text across Dutch, English, French, German, Italian, Polish, Portuguese, Spanish, and Swedish.

For full API documentation, see [docs.reson8.dev](https://docs.reson8.dev).

## Installation

```bash
pip install livekit-plugins-reson8
```

## Usage

```python
from livekit.plugins import reson8

stt = reson8.STT(
    api_key="your-api-key",   # or set RESON8_API_KEY
    language="nl",
)
```

### With an Agent

```python
from livekit.agents import Agent, AgentSession
from livekit.plugins import reson8

agent = Agent(
    instructions="You are a helpful assistant.",
    stt=reson8.STT(language="nl"),
    llm=...,  # any LLM
    tts=...,  # any TTS
)

session = AgentSession()
await session.start(agent=agent, room=ctx.room)
```

## Configuration

| Parameter | Env var | Default | Description |
|---|---|---|---|
| `api_key` | `RESON8_API_KEY` | *required* | API key from [console.reson8.dev](https://console.reson8.dev) |
| `api_url` | `RESON8_API_URL` | `https://api.reson8.dev` | API base URL |
| `language` | -- | `nl` | Language code (`nl`, `en`, `fr`, `de`, `it`, `pl`, `pt`, `es`, `sv`) |
| `custom_model_id` | -- | `None` | ID of a [custom model](https://docs.reson8.dev/documentation/general/glossary/) for domain-specific transcription |
| `sample_rate` | -- | `16000` | Audio sample rate in Hz |
| `include_timestamps` | -- | `False` | Include timing data on transcripts |
| `include_words` | -- | `False` | Include word-level detail |
| `include_confidence` | -- | `False` | Include confidence scores |

## Links

- [Reson8 Documentation](https://docs.reson8.dev)
- [Reson8 Console](https://console.reson8.dev)
- [API Reference](https://docs.reson8.dev/api/)
- [GitHub](https://github.com/reson8lab/livekit-plugins-reson8)
- [PyPI](https://pypi.org/project/livekit-plugins-reson8/)
