Fast STT (Speach-to-Text) Web UI with mlx-whisper
-
Updated
Sep 23, 2025 - Python
Fast STT (Speach-to-Text) Web UI with mlx-whisper
Speech2Text
把抖音视频链接变成可读的 Markdown 文字稿。in 抖音 URL → out 分段格式化 .md 文件
Cross-platform CLI to download & transcribe podcasts locally — Apple Podcasts, Xiaoyuzhou, RSS feeds with built-in Whisper speech-to-text (Metal/CUDA/CPU)
A flexible speech recognition toolkit supporting multiple backends (Whisper, Faster-Whisper, WhisperX, SpeechRecognition, Vosk) with CLI and Gradio web interface.
Meeting Transcriber for Desktop using Whisper
Claude Code Skill for video/audio transcription with MLX Whisper on Apple Silicon. Produces accurate Traditional Chinese (Taiwan) transcripts + structured summaries with 8 scene templates. Free, local, no API costs.
A simple CLI script that transcribes your voice memo to a txt file with timestamp
Claude Code skill that turns a podcast URL into structured deep-reading HTML: local mlx-whisper transcription, shownotes-aligned chapters, optional product analysis.
Point it at a video, image, or PDF — get structured JSON. uvx vidlizer[mcp]. Runs local (Ollama/gemma4, LM Studio, oMLX) or cloud (OpenRouter). CLI + MCP server for Claude Code, Cursor, and Claude Desktop.
Automatically extract VTuber personality from Bilibili recordings.
a tool to download, transcribe and perform semantic/keyword searches on audio files, all locally
Import Google Meet and Lark/Feishu meeting transcripts into Obsidian with MLX Whisper and OpenAI transcription fallbacks.
Voice-bank-first speaker labelling for the Plaud Note family. Local, macOS Apple Silicon, AGPL-3.0.
Privacy-first voice-to-text for macOS — local STT via mlx-whisper with app-aware formatting, AI post-processing, and push-to-talk dictation
End-to-end Xiaoyuzhou FM podcast transcription & AI summarization — mlx-whisper + DeepSeek, native on Apple Silicon.
Real-time audio transcription monitoring system with AI-powered note generation using DeepSeek API
Transcribe or translate audio and video files using the OpenAI Whisper large-v3-turbo model on Apple Silicon with MLX.
Convenience wrapper over ffmpeg and mlx-whisper to quickly transcribe OBS recordings
Local Apple Silicon audio/video transcription with MLX Whisper, Parakeet, drop-folder, CLI, Tk, and web upload workflows.
Add a description, image, and links to the mlx-whisper topic page so that developers can more easily learn about it.
To associate your repository with the mlx-whisper topic, visit your repo's landing page and select "manage topics."