whispercpp

TalkiTo lets developers interact with AI systems through speech across multiple channels (terminal, API, phone). It can be used as both a command-line tool and a Python library.

speech to text gui for different (e.g. Whisper, Voxtral) models and backends, including whisper.cpp, crispasar, mlx-whisper, faster-whisper, ctranslate2; applies pyannote for diarization

Web API that summarizes multimedia from various sources using modern AI tools.

Python wrapper for Whisper.cpp

A Maubot to transcribe audio messages using local open-source libraries

Offline speech-to-text for Linux and macOS, triggered by a desktop shortcut. Powered by whisper.cpp.

whispr is a transcription pipeline built around OpenAI's Whisper model. It supports four backends (three interchangeable general-purpose ones plus an optional Mega-ASR specialist for degraded audio), parallel chunk processing, automatic fallback, and multiple output formats.

CLI to transcribe YouTube audio to clean JSON + SRT using local Whisper/whisper.cpp or cloud engines (Gemini/OpenAI/ Deepgram). Supports chapters, summaries, caching, and resilient retries.

Local-first Python CLI that turns webinar audio and slide videos into transcripts, reports, scenes, diagnostics, and optional LLM-polished notes.

One-command lecture pipeline: video/audio -> audited Markdown note

voice-powered note taking with whispercpp/chatgpt api

Python wrapper around whisper.cpp server

Another attempt at an LLM driven voice assitant, but with better transcription and better TTS

Team Sonare - Qualcomm Hackathon Sep 2025

Offline AI Video Translator powered by Whisper.cpp and Ollama

Fully local YouTube transcription + summarization in one portable executable: yt-dlp + whisper.cpp + Ollama. No cloud, no API keys.

🎙️ GPU-accelerated video/audio transcription studio powered by faster-whisper and FFmpeg. Batch-process media locally or on Google Colab and generate timestamped TXT, SRT, and Markdown study notes with resumable processing and live progress tracking.

Fast, private, system-wide voice dictation for Windows 10 & 11. Hold a key, talk, release. Clean text appears in whatever app you're using. Powered by Desert Ant Labs models (Voz, Clear, Uhm, Redact). Speech recognition and noise cleanup run entirely on your machine, and audio never leaves your PC.