Yapsnap – CPU-only transcription for YouTube, TikTok, X, Instagram
Local CPU transcription that beats cloud APIs on speed and privacy.
Snap any video URL or audio file into plaintext. No GPU. No cloud. One command.
CPU-only ONNX transcription when Whisper.cpp already handles this well.
Developers and content creators needing offline transcription
Whisper.cpp · faster-whisper · AssemblyAI
Local CPU transcription that beats cloud APIs on speed and privacy.
Matches pyannote on accuracy, runs 8x faster on CPU, no signup—genuine infrastructure win.
Outputs ready-to-use Markdown with speaker diarization and timestamps, accepts Apple Podcasts/YouTube/RSS links, and can run fully locally or use ElevenLabs for higher-quality diarization. Not groundbreaking — speech-to-text pipelines already exist — but the one-command UX, RSS browsing/search flags, and explicit local-mode make it genuinely useful for folks who want tidy transcripts without wiring together multiple tools.
CoreML-powered diarization that's 37x faster than pyannote on Apple Silicon.
Floating overlay dictation that keeps your keyboard - Termux command mode converts speech to CLI.
It pairs WhisperX-grade transcription (speaker diarization and word-level timestamps) with optional multi-LLM analysis — summaries, Q&A, sentiment, topics and even fact-checking — plus YouTube import and standard export formats. Being vendor-agnostic and offering fact-checking is a smart differentiator, but the space is crowded (Descript/Otter/etc.); clearer accuracy numbers, pricing, or unique workflow hooks would make this stand out.