https://github.com/outspeed-ai/outspeed
Python SDK to build realtime AI applications on voice and video.
https://github.com/outspeed-ai/outspeed
ai chatbot multimodal realtime voice-assistant webrtc
Last synced: about 1 year ago
JSON representation
Python SDK to build realtime AI applications on voice and video.
- Host: GitHub
- URL: https://github.com/outspeed-ai/outspeed
- Owner: outspeed-ai
- License: other
- Created: 2024-09-18T00:06:00.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2024-11-27T03:54:44.000Z (over 1 year ago)
- Last Synced: 2025-04-07T09:07:18.425Z (about 1 year ago)
- Topics: ai, chatbot, multimodal, realtime, voice-assistant, webrtc
- Language: Python
- Homepage:
- Size: 1.49 MB
- Stars: 386
- Watchers: 4
- Forks: 23
- Open Issues: 4
-
Metadata Files:
- Readme: README.md
- License: LICENSE.txt
Awesome Lists containing this project
README
[](https://twitter.com/outspeedAI) [](https://github.com/outspeed-ai/outspeed)
[](https://pypi.python.org/pypi/outspeed)
[](https://pepy.tech/project/outspeed)
[Community](https://discord.gg/cmffw6syvp) | [Docs](https://docs.outspeed.com) | [Dashboard](https://app.outspeed.com)
# Outspeed
Outspeed is a PyTorch-inspired SDK for building real-time AI applications on voice and video input. It offers:
- Low-latency processing of streaming audio and video
- Intuitive API familiar to PyTorch users
- Flexible integration of custom AI models
- Tools for data preprocessing and model deployment
Ideal for developing voice assistants, video analytics, and other real-time AI applications processing audio-visual data.
## Install
You can install `outspeed` SDK from pypi using
```
pip install "outspeed[silero]>=0.1.143"
```
This would install the core `outspeed` package.
Read our [quickstart guide](https://docs.outspeed.com/examples/quickstart) to get started.
### Usage
Read the [docs](http://docs.outspeed.com) to learn more about the SDK.
To deploy your realtime function on Outspeed's infra, you can use the `outspeed deploy` CLI.
```
# functions.py contains your realtime function code
outspeed deploy --api-key= functions.py
```
[Contact us](mailto:contact@outspeed.com) to get an API key and deploy.
Once deployed, you can use the playground in the examples repo to test the deployed code.
### Examples
All the examples are available in the `examples` folder.
To install the package so that all examples run, use:
```
pip install "outspeed[silero]>=0.1.143"
```
Or, if you're using poetry:
```
poetry add 'outspeed[silero]'
```
This will install all the additional libraries that are required for examples to work.
---
### Logging
To develop on top of the SDK, set environment variable `DEV_INFO` or `DEV_DEBUG` to get logs from the SDK for the corresponding log level.
## Roadmap
| Feature | Status | Target Release |
| ------------------------------------------------------------ | ---------- | -------------- |
| Local STT | On the way | Q4 2024 |
| DeepReel Integration (Human Clone) | On the way | Q4 2024 |
| Long Conversation Support | Planned | Q4 2024 |
| Local Model Vision and Text (With Ollama, and vision models) | Planned | Q4 2024 |
| Call Recording | Planned | Q4 2024 |
| Wakeup Word | Planned | Q4 2024 |
| On device models | Planned | Q4 2024 |
| Local TTS | Planned | Q4 2024 |
## Run CircleCI Tests Locally
Make sure docker is installed and running.
```
brew install circleci
circleci local execute run-tests
```
## Contribute
We welcome contributions to the Outspeed SDK! If you're interested in contributing, please submit a PR or [contact us](mailto:contact@outspeed.com).