skills.rest
Aadi-110i
Aadi-110iCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

speech-to-text

Transcribe audio files to text using ElevenLabs Scribe and Whisper models via the inference.sh CLI.

Updated Jul 28, 2026
Search Tags:#subtitles#transcription#whisper#audio#elevenlabs#speech-to-text#diarization
One-click install
npx skills add https://github.com/Aadi-110i/PEP-PROJECT --skill speech-to-text-aadi-110i
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: speech-to-text
Source: https://github.com/Aadi-110i/PEP-PROJECT/tree/main/skills/speech-to-text
Command: npx skills add https://github.com/Aadi-110i/PEP-PROJECT --skill speech-to-text-aadi-110i

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Converting audio recordings into written text manually is slow and error-prone. This Skill automates speech-to-text transcription, translation, and speaker diarization through hosted AI models accessible from the command line. ## Core Features & Use Cases - Multi-Model Transcription: Choose between ElevenLabs Scribe v2 (diarization, 90+ languages), Fast Whisper Large V3 (speed), or Whisper V3 Large (accuracy). - Timestamps & Translation: Generate timestamped segments for subtitles and translate foreign-language audio into English. - Video Workflows: Extract audio from video files and pipe transcripts into captioning tools. - Use Case: Transcribe a recorded podcast episode with timestamps, then feed the transcript into a captioning app to produce subtitles for the video version. ## Quick Start Transcribe the audio file at this URL to text with timestamps using the speech-to-text skill.

Frequently Asked Questions about speech-to-text

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I transcribe audio to text with Whisper?▼

Run the belt CLI command with an app ID like infsh/fast-whisper-large-v3 and pass an input JSON containing the audio_url. The output returns JSON with the full transcription text and detected language.

ElevenLabs Scribe vs Whisper for transcription, which should I use?▼

ElevenLabs Scribe v2 offers 98%+ accuracy, speaker diarization, and 90+ languages, making it best for multi-speaker content. Fast Whisper Large V3 is better for quick transcription, while Whisper V3 Large targets highest accuracy.

Can Whisper translate audio to English?▼

Yes, Whisper V3 Large supports translation by setting the task parameter to translate in the input JSON. This converts non-English audio directly into English text.

How do I transcribe audio from a video file?▼

First extract the audio using the infsh/video-audio-extractor app, then pass the resulting audio URL to a transcription model. The transcript can then feed into captioning apps for subtitles.

Does speech-to-text transcription support timestamps?▼

Yes, set the timestamps parameter to true in the input JSON. The output includes a segments field with timestamped portions of the transcription, suitable for subtitle generation.

What languages does Whisper transcription support?▼

Whisper supports 99+ languages including English, Spanish, French, German, Italian, Portuguese, Chinese, Japanese, Korean, Arabic, Hindi, and Russian. The detected language is returned in the output JSON.

Related Skills

Explore More Content & Communication Skills→
Pixazo-AIPixazo-AI

audio-extract-api

Extract audio tracks from video files as mp3 or m4a via the Pixazo API.

Official
Basic
gupsammygupsammy

youtube-transcript

Retrieve YouTube transcripts and captions from video URLs using yt-dlp.

Community
Advanced
inference-shinference-sh
688

ai-avatar-video

Generates AI avatar and talking head videos via the inference.sh CLI.

Official
Intermediate
gabrielkoerichgabrielkoerich
5

openai-whisper

Transcribe spoken audio into text locally using the Whisper CLI.

Community
Intermediate