Speech To Text

This hooks Claude up to ElevenLabs Scribe and Whisper models through the inference.sh CLI. You get three transcription options: ElevenLabs Scribe v2 with 98%+ accuracy and speaker diarization, Fast Whisper Large V3 for speed, or Whisper V3 Large for maximum accuracy. It handles timestamps, multi-language support, and translation to English. The workflow examples are solid, especially the video subtitling pipeline that chains transcription with caption generation. Works well for meeting recordings, podcasts, and voice notes. You'll need the belt CLI installed, but once that's done the commands are straightforward JSON over the command line.

skills.sh installs: 1.1K
GitHub stars: 804
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add inference-sh/skills --skill speech-to-text --agent claude-code

Installs into .claude/skills of the current project.

Files

Install the belt CLI skill: npx skills add belt-sh/cli

Speech-to-Text

Transcribe audio to text via inference.sh CLI.

Speech-to-Text

Quick Start

Requires inference.sh CLI (belt). Install instructions

belt login

belt app run infsh/fast-whisper-large-v3 --input '{"audio": "https://audio.mp3"}'

Available Models

Model	App ID	Best For
ElevenLabs Scribe v2	`elevenlabs/stt`	98%+ accuracy, diarization, 90+ languages
Fast Whisper V3	`infsh/fast-whisper-large-v3`	Fast transcription
Whisper V3 Large	`infsh/whisper-v3-large`	Highest accuracy

Examples

Basic Transcription

belt app run infsh/fast-whisper-large-v3 --input '{"audio": "https://meeting.mp3"}'

With Timestamps

belt app sample infsh/fast-whisper-large-v3 --save input.json

# {
#   "audio": "https://podcast.mp3",
#   "return_timestamps": "sentence"
# }

SKILL.md on GitHub

Sponsors

Promote your product hereReach 125k+ visitors monthly Promote your product hereReach 125k+ visitors monthly

Agent CaffeineSponsoredClose your lid, come back to finished work

SnugSponsoredThe clipboard manager for the AI era Promote your product hereReach 125k+ visitors monthly

WaxSponsoredBlock anything with supervision, without erasing your iPhone Promote your product hereReach 125k+ visitors monthly

knobsSponsoredSee your site on any phone, any day, in any language

Details

Repository: github.com/inference-sh/skills
Categories: Automation & Workflows, CLI & Terminal, Generative Media, Video & Audio Editing
First seen: Jun 3, 2026

Speech To Text

Install

Files

Speech-to-Text

Quick Start

Available Models

Examples

Basic Transcription

With Timestamps

Details

More from inference-sh/skills

Recommended