WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)

🎩 Alfred 5 Workflow for using OpenAI GPT-3.5 and GPT-4 🤖 with Text Completion/Chat API 📝 It also allows image generation using DALL-E API 🖼️ and speech-to-text conversion using Whisper API 💬

Speech to Text to Speech. Song now playing. Sends text as OSC messages to VRChat to display on avatar. (STTTS) (Speech to TTS) (VRC STT System)

NeMo: a toolkit for conversational AI

background voice detection program that listens for a wake word and activates transcription mode

Eden AI: simplify the use and deployment of AI technologies by providing a unique API that connects to the best possible AI engines

Medkit is a Python library for facilitating the extraction of features from various modalities of patient data. Mirror of https://gitlab.inria.fr/heka/medkit

Official JavaScript SDK for Deepgram's automated speech recognition APIs.

Voice Controlled Robot with ROS 🤖

This is openAi powered interview site where the user can join and take in interview on the topic of their choice. It is done using React for frontend and nodeJS at the backend level the API documentations for the backend is found below in the readme.md. For demo check this https://drive.google.com/file/d/1DDqFpEOaA1chXdDad9RQ08dK7Ms-WS4g/view?usp

Translate the voice in a different language from the original language in real time.

Speech to text bot for Discord

Unofficial No Such Thing As A Fish episode transcripts.

A PyTorch-based Speech Toolkit

Listening and Speaking

Open Voice OS Status Page

OpenAI Whisper ASR Webservice API

Home Manager GPT is a text to speech chat gpt that can be used to control your entire house. ask verbal questions and get verbal answers from google speech recognition.

minimal deep learning framework

Voicegain Enterprise Speech-to-Text Platform (API, Portal, etc.)

Downloads a youtube video, converts speech to Ukrainian text, and adds pronunciation stress accents.

Real-time transcription using faster-whisper

Speech Note Linux app. Note taking, reading and translating with offline Speech to Text, Text to Speech and Machine translation.

Demonstrates Voice Recognition, Text to Speech, Language Translation, OAuth2, Image Generation, Face Detection and Voice Chatbot. Source code and Documentation for my 2023 ADUG Symposium Talk.

Dockerfile for WhisperX: Automatic Speech Recognition with Word-Level Timestamps and Speaker Diarization (Dockerfile and CI image build)

Port of OpenAI's Whisper model in C/C++

Talking with ChatGPT is a breeze

Modular OSC program creator, toolkit, and router made for VRChat. Show your heartrate, time, hardware stats, speech to text, control Spotify, and more! Includes drag-and-drop prefabs for your avatar.

Open source, local, and self-hosted Amazon Echo/Google Home competitive Voice Assistant alternative

Repository for multilingual speech data resources for native languages of Zambia.