LogoClawIndex
CasesSkillsAbout
LogoClawIndex

speech-to-text - Transcribe audio to text using Whisper AI models

Transcribes audio files to text using Whisper models via inference.sh CLI

Tags

Updated: 2026-02-09
audio transcriptionspeech recognitionmultilingualsubtitlestranslation

Capabilities

transcribe audio to texttranslate audio to englishgenerate timestampsdetect language

Typical Inputs

audio file URLinference.sh CLIWhisper model selection

Typical Outputs

transcribed texttimestamped segmentslanguage detection result

What this skill does

  • transcribe audio to text
  • translate audio to english
  • generate timestamps
  • detect language

Inputs

  • audio file URL
  • inference.sh CLI
  • Whisper model selection

Outputs

  • transcribed text
  • timestamped segments
  • language detection result

Requirements

  • inference.sh CLI installation
  • authentication via infsh login
  • available Whisper model apps

Source

  • Spec: SKILL.md

ClawIndex

OpenClaw Skills & Use Case Index

ClawIndex is an ecosystem-driven index of OpenClaw skills and real-world use cases.

Index

Skills·
Cases

Meta

About·
Disclaimer·
Email·
GitHub
© 2026 ClawIndex All Rights Reserved.