Score7.7
Popularity281.0
Risklow
TierSilver
Score breakdown
Usefulness8.0
Novelty8.0
Momentum7.0
Maturity8.1
Open-source/build8.4
Evidence8.0
Workflow potential8.8
Setup ease8.8
Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.
Why it matters
Useful for **journalists, researchers, and power users who need fast offline transcription of video URLs and audio files** — yapsnap is the Apache-2.0 CPU-only offline video/audio-to-plaintext transcriber, streams any YouTube / X / TikTok / Reels URL or local file through yt-dlp + ffmpeg + Zipformer transducer (Kroko English) to a .txt, no GPU, no cloud, no API keys, ~80 MB model downloads once an
Who should use it
**Journalists, researchers, and power users who need fast offline transcription of video URLs and audio files** — yapsnap is the Apache-2.0 CPU-only offline video/audio-to-plaintext transcriber**Anyone who needs a Whisper alternative without GPU or cloud dependency** — Kroko English Zipformer transducer (sherpa-onnx) is CPU-only and offline; no CUDA, no M-series tricks, plain old cores**Teams that need privacy-preserving transcription** — audio never leaves your machine; no API keys, no quotas, no cloud sync**Teams that need multi-source support** — any URL yt-dlp understands (YouTube, X, TikTok, Instagram Reels, direct .mp4/.mp3 links) plus local files**Teams that need multi-language support** — English out of the box; French, German, Spanish, Italian, Portuguese, Dutch, Swedish, Swiss German, Hebrew, and Turkish are a one-flag `--lang` swap**Teams that need timestamps** — `--timestamps` adds `[MM:SS]` per sentence; timing stays correct even when transcribing at 2x**Teams that need speaker diarization** — `--diarize` answers 'who spoke when' and prefixes each line with `SPEAKER_00`, `SPEAKER_01`, etc.**Teams that need a lean dep footprint** — `sherpa-onnx`, `numpy`, `yt-dlp` — that's the whole runtime, no PyTorch, no cloud SDKs**CI / automation pipelines** — yapsnap is a single CLI, can be scripted in any language that can call subprocess**Teams that need a quick way to make meeting notes searchable** — point yapsnap at a recorded meeting, get a .txt transcript, search the text**Apache-2.0 commercial platforms** — plain Apache-2.0, no per-file carve-outs, no SaaS-embedding caveat, no commercial-use thresholdEvaluation: (1) Install ffmpeg on PATH (one-time, per OS — see README for OS-specific instructions). (2) `pip install yapsnap` (or `pip install .` from a clone). (3) `yapsnap https://www.youtube.com/watch?v=...` (URL or local file). The first run downloads the model (~80 MB); every run after is offline. For testing CPU performance: time `yapsnap` on a 30-minute video — should complete in less than the video duration on a modern laptop. For testing multi-language: `yapsnap --lang fr interview.mp3` for a French interview. For testing timestamps: `yapsnap --timestamps meeting.mp4`. For testing diarization: `yapsnap --diarize panel-discussion.mp3` (output prefixes each line with `SPEAKER_00`, etc.). For the open-source status: plain Apache-2.0, kouhxp, no per-file carve-out, no SaaS-embedding caveat, no commercial-use threshold. For the maturity caveat: at 281 stars and 11 forks, yapsnap is a relatively new project — fine for early adoption, monitor releases for stability and language support additions. The English model is the primary (Kroko English); other languages are a one-flag swap but with potentially lower accuracy than dedicated models like Whisper-large-v3 for those languages. ffmpeg is a hard prerequisite and must be on PATH — users on Windows may need to add ffmpeg to their PATH manually
Who should skip it
Move on from kouhxp/yapsnap if the licensing terms, language support, or platform requirements do not fit your project.
About this signal
kouhxp/yapsnap is tracked by RepoRadar as a apache-2.0 cpu-only offline vide in the kouhxp/yapsnap (Apache-2.0, kouhxp) is the CPU-o section. It was first seen on 2026-06-26 and last updated on 2026-06-26. The current verdict is 'try now' with a Silver tier and easy setup difficulty. The standout signals for kouhxp/yapsnap are workflow potential (8.8) and setup ease (8.8), while momentum (7.0) trails — that balance shapes where it fits best. This page summarizes the evidence RepoRadar has captured from captured source metadata. The score, tier, risk label, and verdict on this page are never influenced by sponsorship, ads, or tips — they reflect only the usefulness, popularity, novelty, momentum, maturity, and evidence signals described in the RepoRadar methodology.
How this item is evaluated
RepoRadar assigned kouhxp/yapsnap a composite score of 7.7 out of 10, placing it in the Silver tier. This score combines weighted sub-signals: usefulness (35%), novelty (18%), momentum (14%), maturity (10%), open-source/build quality (7%), evidence quality (6%), workflow potential (6%), and setup ease (4%). Popularity is tracked separately at 281.0 and never affects the composite score or tier. The risk label of 'low' reflects inherent user-impacting hazards, not generic novelty. Items with no risk flag may still require normal code review before production use.
Risk explanation
maturity caveat — at 281 stars and 11 forks; yapsnap is a relatively new project; fine for early adoption; monitor releases for stability and language support additions. The English model is the primary (Kroko English).
Evidence links
Closest alternatives / related signals
yapsnapkouhxpcpu-onlyoffline-transcriptionvideo-to-textaudio-to-textspeech-to-textplaintext-transcript
