Skip to content
TrustedSkillsbeta
Back to all skills

Faster Whisper

Listed
ThePlasmak·v1.5.1·ai-ml·MIT

Local speech-to-text using faster-whisper — 4-6x faster than OpenAI Whisper with identical accuracy. GPU acceleration, SRT/VTT/TTML subtitles, speaker diarization, and chapter detection.

Repository

Install on your platform

Showing OpenClaw.

  1. 1

    Run this in your terminal

    terminal
    $ openclaw skills install faster-whisper

What we know about this skill

Publisher

ThePlasmak

Taken from the source listing. We haven't verified who controls this account.

Install target

Pinned to 1c8d6a68

Installs fetch a stored snapshot of that commit, so the code can't change after the fact.

No human has reviewed this code. The checks below are a static scan of the files at one commit — nobody has run this skill or judged whether it works. A skill runs with whatever access you give your agent, so read the source before you install it.

Automated safety checks

scanned

This skill failed 1 of 6 checks. A failure is not proof of bad intent; it means something in the code needs a human to look at it before you run it.

  • No undeclared network calls: failed

    Contacts 5 hosts that are neither well-known infrastructure nor declared in the skill's frontmatter: download.pytorch.org, ffmpeg.org, hf.co, python.org, youtube.com.

    Every host the skill dials — from its scripts, its config endpoints or the commands it tells the agent to run — is either well-known package and API infrastructure or declared in its own frontmatter. Links in documentation are not counted.

    Hosts contacted

    www.w3.orgstandardshf.coundeclaredyoutube.comundeclareddownload.pytorch.orgundeclaredpython.orgundeclaredffmpeg.orgundeclared

    What it found (3 of 14)

    • scripts/transcribe.py:1132contacts hf.co
      "  and accepted: https://hf.co/pyannote/speaker-diarization-3.1",
    • setup.sh:149contacts hf.co
      echo "               and model agreement at https://hf.co/pyannote/speaker-diarization-3.1"
    • setup.sh:317contacts hf.co
      echo "   2. Accept model agreement: https://hf.co/pyannote/speaker-diarization-3.1"

  • Declares what it does: passed

    SKILL.md parses and declares a name and a description.

    SKILL.md exists, its frontmatter parses, and it declares a name and a description.

  • No obfuscated payloads: passed

    No encoded or obfuscated payloads.

    No base64, hex or compressed blob is decoded and then executed, and no encoded shell commands.

  • No credential access: passed

    Reads no keys, tokens, keychains or credential files.

    Neither the code nor the SKILL.md instructions read SSH keys, cloud credentials, keychains, token stores, browser cookie databases or dotfiles that hold secrets.

  • No pipe-to-shell installers: passed

    No pipe-to-shell or download-and-run installers.

    No `curl … | sh` pattern, in the code or in the instructions, that runs code fetched at run time.

  • Pinned to a commit: passed

    Scanned theplasmak/faster-whisper at 1c8d6a682c.

    The exact upstream commit SHA that was scanned is recorded, so the result refers to specific bytes.

Commit
1c8d6a682c
Manifest
SKILL.md
Scanned
11 files, 5,612 lines
This is a static scan, not a review. It reads the skill's files; it does not run them, and it cannot tell you whether the skill is any good or whether the code does what its description says. A skill runs with whatever access you give your agent.
What each check looks for →

About this skill

What it does

faster-whisper provides local speech-to-text transcription capabilities that are significantly faster – up to 6 times quicker – than the standard OpenAI Whisper model while maintaining comparable accuracy. It supports GPU acceleration for improved performance and offers features like SRT/VTT/TTML subtitle generation, speaker diarization (identifying different speakers), and automatic chapter detection within audio files. This allows for efficient transcription of long-form audio content without sacrificing quality.

When to use it

  • Transcribing lengthy lectures or presentations where speed is crucial.
  • Generating subtitles for videos in SRT, VTT, or TTML formats for accessibility or distribution.
  • Analyzing meeting recordings and identifying different speakers involved in the conversation.
  • Creating chapter markers within podcasts or audiobooks to improve navigation.

Key capabilities

  • GPU acceleration for faster transcription speeds
  • SRT/VTT/TTML subtitle generation
  • Speaker diarization
  • Chapter detection

Example prompts

  • "Transcribe this audio file and generate an SRT subtitle file."
  • "Identify the speakers in this meeting recording."
  • "Create chapter markers for this podcast episode based on pauses and content changes."

Tips & gotchas

  • A GPU is highly recommended to take full advantage of faster-whisper's speed improvements. Without a GPU, transcription will be slower.
  • The accuracy of speaker diarization can depend on audio quality and the clarity of different speakers’ voices.

Requirements

Required binaries

python3

Tags

whispertranscriptionspeech-to-textgpusubtitlesdiarizationlocal