Skip to main content

No project description provided

Project description

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 to get started.

Usage

Read the docs 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=<your-api-key> functions.py

Contact us 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.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

outspeed-0.2.5.tar.gz (317.8 kB view details)

Uploaded Source

Built Distribution

outspeed-0.2.5-py3-none-any.whl (82.2 kB view details)

Uploaded Python 3

File details

Details for the file outspeed-0.2.5.tar.gz.

File metadata

  • Download URL: outspeed-0.2.5.tar.gz
  • Upload date:
  • Size: 317.8 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.8.3 CPython/3.12.7 Darwin/23.6.0

File hashes

Hashes for outspeed-0.2.5.tar.gz
Algorithm Hash digest
SHA256 acdbf45597c93f7fa3207745f484b9dc5cf8f443be76d7c9d78a465e2ff53fc9
MD5 2dbb7aad47052833b8a4c0debefed4ba
BLAKE2b-256 02febef3826bbc52569300c790e1a35b1c654670605a2c67ca3de807d159843d

See more details on using hashes here.

File details

Details for the file outspeed-0.2.5-py3-none-any.whl.

File metadata

  • Download URL: outspeed-0.2.5-py3-none-any.whl
  • Upload date:
  • Size: 82.2 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.8.3 CPython/3.12.7 Darwin/23.6.0

File hashes

Hashes for outspeed-0.2.5-py3-none-any.whl
Algorithm Hash digest
SHA256 a1edfe964c9634f114bcd2047006a2335f898e7ddc84ea40ba003534bbf76b62
MD5 85cb865603840b66297462e3895ce928
BLAKE2b-256 700f8ed23f0043f465f3730167f25547a540467cbf0928f37a77732a20b48dbd

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page