Speech-to-text, 3x faster than Whisper, remote FREE GPU

3x Faster than Whisper, Speech-to-text transcription with sentence-level timestamps on remote (FREE) L4 GPU. Trigger when user says: transcribe, speech to te...

What to consider before installing/running this skill: - The skill uses Modal (your Modal CLI/token) and will create and use Modal volumes to upload audio and store models/results. Uploaded audio and generated transcripts live in those volumes under your Modal account — treat that as remote storage. - The code contains a step that removes ~/.cache and symlinks it to the models volume when the model loads. If you accidentally run transcribe.py locally rather than via 'modal run', this could delete your local ~/.cache (which may contain other cached credentials or valuable caches). Do NOT run the Python file directly on your machine unless you inspect and modify that behavior first. - Dependencies are installed from PyPI (faster-whisper, stable-ts). That is expected for model inference, but you must trust those packages. The image also apt-installs ffmpeg. - The README mentions HF_TOKEN as optional for higher rate limits; you should only set that if you trust the skill to access Hugging Face on your behalf. - There is at least one apparent bug/typo in transcribe.py (truncated 'jso' usage) — expect the code may need fixing before reliable use. Recommendations: 1) Inspect transcribe.py and remove/modify the code that deletes ~/.cache (or ensure it runs only in an isolated container). 2) Run the skill in an isolated Modal account or project where persistent volumes and billing are acceptable. 3) Backup your local ~/.cache before trying local experimentation. 4) If you need stronger assurance, run the container build in an isolated environment and review all third-party dependencies (PyPI packages) before executing on real data.

Type: OpenClaw Skill Name: speech-transcribe Version: 1.3.1 The skill provides a legitimate speech-to-text transcription pipeline using the Modal platform and Whisper models. It includes well-structured logic in `transcribe.py` for parallelizing ffmpeg conversion and model loading, and the `SKILL.md` instructions correctly guide the AI agent through the workflow of uploading files, running the remote GPU task, and retrieving results. No indicators of data exfiltration, malicious execution, or prompt injection were found.