Ingest, parse, and optimize any data format ➡️ from documents to multimedia ➡️ for enhanced compatibility with GenAI frameworks

Project that allows one to use a microphone with OpenAI whisper.

⚡ 一款用于自动语音识别 (ASR)、翻译的高性能异步 API。不需要购买Whisper API，使用本地运行的Whisper模型进行推理，并支持多GPU并发，针对分布式部署进行设计。还内置了包括TikTok、抖音等社交媒体平台的爬虫，可实现来自多个社交平台的无缝媒体处理，为媒体内容数据自动化处理提供了强大且可扩展的解决方案。

Private voice keyboard, agent, AI chat, images, webcam, recordings, voice control with >= 4 GiB of VRAM.

A stream-translator fork with VAD based audio slicing & GPT / Gemini translation.

whisper.cpp bindings for python

A feature-rich Python-based Telegram bot for OpenAI API & Perplexity API

YouTube Video Summarization App built using open source LLM and Framework like Llama 2, Haystack, Whisper, and Streamlit. This app smoothly runs on CPU as Llama 2 model is in GGUF format loaded through Llama.cpp.

Live translation tool utilizing OpenAI's Whisper model for real-time audio transcription/translation with BYOK OpenAI API key for your choice of language.

WhisperX FastAPI integration

Drop-in replacement for the OpenAI's Whisper API using the same API but running locally

A working Speech to Speech AI assistant that can interact with you, manage your system, and more!

Discord bot that downloads and transcribes twitter space audio file

This repository provides a Flask app that processes voice messages recorded through Twilio or Twilio Studio, transcribes them using OpenAI's Whisper ASR, generates responses with GPT-3.5, and sends the replies as SMS using Twilio.

YASS.ai - Team Orange's entry to the Flow AI Hackathon 2023

用 Open AI 的 Whisper API 轉譯字幕的 Web UI。

🎧 Submind is a modern PyQt6 app for generating subtitles (SRT) using Whisper AI. Supports drag & drop, batch processing, and auto translation in a sleek UI.

A simple desktop application that provides instant voice-to-text transcription using OpenAI's Whisper API, specifically enhanced for developers working with AI tools like Cursor, Warp, GitHub Copilot, and other AI assistants.

Speech2Text

A subtitle generator for videos up to 10GB, automatically transcribing and translating spoken content into Brazilian Portuguese. Ideal for multilingual content, this tool creates accurate `.srt` files for seamless integration with video players.