Speech To Text

Name: Speech To Text
Author: inference-sh

inference-sh/skills

575 installs
680 repo stars
Updated August 3, 2026
inference-sh/skills

Speech-to-text is an agent skill that transcribes meetings, podcasts, and voice notes into searchable text or subtitles through inference.sh so developers who need STT can run Whisper and ElevenLabs Scribe models without

About

Speech-to-text is an inference.sh agent skill that transcribes audio via the belt CLI using ElevenLabs Scribe v2, Fast Whisper Large V3, and Whisper V3 Large. It supports transcription, translation, multi-language output, timestamps, speaker diarization, and audio event tagging for meetings, podcasts, subtitles, and voice notes. Developers reach for speech-to-text when they need production STT from the terminal or agent workflows instead of implementing Whisper or ElevenLabs SDK calls directly.

Runs ElevenLabs Scribe v2, Fast Whisper Large V3, and Whisper V3 Large via inference.sh app IDs
Supports diarization, timestamps, multi-language transcription, translation, and audio event tagging
Meeting, podcast, subtitle, and voice-note oriented trigger phrases in SKILL.md
Quick start: `belt login` then `belt app run` with an `audio_url` JSON payload
Install path documented: `npx skills add belt-sh/cli` for the belt CLI skill

Speech To Text by the numbers

575 all-time installs (skills.sh)
+9 installs in the week ending Aug 2, 2026 (Skillselion tracking)
Ranked #1,626 of 16,546 AI & Agent Building skills by installs in the Skillselion catalog
Security screen: MEDIUM risk (skills.sh audit)
Data as of Aug 5, 2026 (Skillselion catalog sync)

npx skills add https://github.com/inference-sh/skills --skill speech-to-text

Add your badge

Show developers this skill is listed on Skillselion. Paste this into your README.

[![Listed on Skillselion](https://skillselion.com/badge/skills/inference-sh/skills/speech-to-text.svg)](https://skillselion.com/skills/inference-sh/skills/speech-to-text)

Installs	575
repo stars	★ 680
Security audit	1 / 3 scanners passed
Last updated	August 3, 2026
Repository	inference-sh/skills ↗

How do you transcribe audio with Whisper via CLI?

Transcribe meetings, podcasts, and voice notes into searchable text or subtitles through inference.sh without wiring Whisper or ElevenLabs APIs by hand.

Who is it for?

Developers adding meeting transcription, podcast captions, or voice-note search who want inference.sh CLI access to Scribe and Whisper models.

Skip if: Real-time streaming STT in a custom WebRTC client or fine-tuning proprietary acoustic models outside inference.sh.

When should I use this skill?

A developer asks to transcribe a meeting, generate subtitles, or convert voice notes to text with Whisper or ElevenLabs.

What you get

Plain-text or timestamped transcript, optional subtitles, speaker labels, and translated text from source audio.

transcript text
subtitles
timestamped segments

By the numbers

ElevenLabs Scribe v2 advertises 98%+ transcription accuracy
Supports 3 STT models: Scribe v2, Fast Whisper Large V3, Whisper V3 Large

Files

SKILL.mdMarkdownGitHub ↗

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

Speech-to-Text

Transcribe audio to text via inference.sh CLI.

Quick Start

Requires inference.sh CLI (belt). Install instructions

belt login

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

With Timestamps

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

# {
#   "audio_url": "https://podcast.mp3",
#   "timestamps": true
# }

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

Translation (to English)

belt app run infsh/whisper-v3-large --input '{
  "audio_url": "https://french-audio.mp3",
  "task": "translate"
}'

From Video

# Extract audio from video first
belt app run infsh/video-audio-extractor --input '{"video_url": "https://video.mp4"}' > audio.json

# Transcribe the extracted audio
belt app run infsh/fast-whisper-large-v3 --input '{"audio_url": "<audio-url>"}'

Workflow: Video Subtitles

# 1. Transcribe video audio
belt app run infsh/fast-whisper-large-v3 --input '{
  "audio_url": "https://video.mp4",
  "timestamps": true
}' > transcript.json

# 2. Use transcript for captions
belt app run infsh/caption-videos --input '{
  "video_url": "https://video.mp4",
  "captions": "<transcript-from-step-1>"
}'

Supported Languages

Whisper supports 99+ languages including: English, Spanish, French, German, Italian, Portuguese, Chinese, Japanese, Korean, Arabic, Hindi, Russian, and many more.

Use Cases

Meetings: Transcribe recordings
Podcasts: Generate transcripts
Subtitles: Create captions for videos
Voice Notes: Convert to searchable text
Interviews: Transcription for research
Accessibility: Make audio content accessible

Output Format

Returns JSON with:

text: Full transcription
segments: Timestamped segments (if requested)
language: Detected language

Related Skills

# ElevenLabs STT (98%+ accuracy, diarization)
npx skills add inference-sh/skills@elevenlabs-stt

# ElevenLabs TTS (reverse direction)
npx skills add inference-sh/skills@elevenlabs-tts

# Full platform skill (all 250+ apps)
npx skills add inference-sh/skills@infsh-cli

# Text-to-speech (reverse direction)
npx skills add inference-sh/skills@text-to-speech

# Video generation (add captions)
npx skills add inference-sh/skills@ai-video-generation

# AI avatars (lipsync with transcripts)
npx skills add inference-sh/skills@ai-avatar-video

Browse all audio apps: belt app store --category audio

Documentation

Running Apps - How to run apps via CLI
Audio Transcription Example - Complete transcription guide
Apps Overview - Understanding the app ecosystem

Related skills

Setup Matt Pocock SkillsScaffold the per-repo configuration that Matt Pocock’s engineering agent skills rely on so they understand the issue tracker, triage labels, and domain documentation la495k196k

Lark AppsConnect Claude, Cursor or custom agents directly to Lark (Feishu) for messaging, document automation, approval workflows and enterprise data access.402k

CavemanSlash token usage by roughly 75% while keeping every technical detail intact when working with Claude Code, Cursor or similar agents.391k94.7k

Lark Skill MakerQuickly turn any Lark/Feishu OpenAPI call or multi-step workflow into a reusable agent skill with its own SKILL.md.386k16k

Running Claude Code Via Litellm CopilotRun Claude Code at a fraction of the cost by routing requests through LiteLLM to the GitHub Copilot Chat API.270k72

Codex PetGenerate a complete Codex Pet spritesheet and metadata from one reference image without needing an OpenAI key or Codex Pro.246k10

Forks & variants (2)

Speech To Text has 2 known copies in the catalog totaling 76 installs. They canonicalize to this original listing.

qu-skills - 72 installs
skills-shell - 4 installs

How it compares

Pick speech-to-text for quick CLI-driven batch transcription via inference.sh; build custom SDK integrations when you need embedded real-time streaming control.

FAQ

Which models does speech-to-text support?

Speech-to-text routes audio through inference.sh to ElevenLabs Scribe v2, Fast Whisper Large V3, and Whisper V3 Large, with Scribe v2 advertising 98%+ accuracy plus diarization.

How do you run speech-to-text?

Speech-to-text uses the inference.sh belt CLI with allowed Bash tooling, letting developers transcribe, translate, timestamp, and diarize audio without wiring Whisper or ElevenLabs APIs manually.

Is Speech To Text safe to install?

skills.sh reports 1 of 3 security scanners passed. Review the Security Audits panel on this page before installing in production.

AI & Agent Buildingautomationllm