skills.rest
dzhechko
dzhechkoCOMMUNITY
Explore all skills by this author →
GitHub

transcribe

Transcribe audio files to text using the Cloud.ru Whisper API.

Updated Aug 27, 2026
Search Tags:#transcription#audio#language detection#speech to text#whisper api#cloud.ru
One-click install
npx skills add https://github.com/dzhechko/cloudru-vm-openclaw-demo --skill transcribe-dzhechko
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: transcribe
Source: https://github.com/dzhechko/cloudru-vm-openclaw-demo/tree/main/archive/project/templates/skills/transcribe
Command: npx skills add https://github.com/dzhechko/cloudru-vm-openclaw-demo --skill transcribe-dzhechko

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires curl, ffmpeg, jq, and includes scripts (resource) components.

What problem does it solve?

This Skill automates the process of converting audio files into text, making spoken content searchable and editable.

Core Features & Use Cases

  • High-Accuracy Transcription: Utilizes Cloud.ru's Whisper API for reliable transcription of over 99 languages.
  • Broad Format Support: Handles various audio inputs including Telegram voice messages (.ogg, .opus) and common recording formats (.mp3, .wav, .m4a).
  • Use Case: Transcribe meeting recordings to create searchable minutes, convert customer service calls for analysis, or make voice notes accessible as text.

Quick Start

Use the transcribe skill to convert the attached audio file 'meeting_recording.ogg' into text.

Frequently Asked Questions about transcribe

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

FAQPage Schema
How do I transcribe audio files to text using the Whisper API?▼

To transcribe audio files to text, this skill sends your audio to the Cloud.ru Whisper API, which automatically detects the language and returns the text transcription for your spoken content.

Can I transcribe Telegram voice messages saved as .ogg or .opus files?▼

Yes, you can transcribe Telegram voice messages in .ogg or .opus formats. The skill normalizes these and other formats like .mp3, .wav, and .m4a to WAV using ffmpeg before processing.

Do I need a Cloud.ru API key to convert speech to text?▼

Yes, you need a Cloud.ru API key to convert speech to text. The skill relies on this key to authenticate requests to the Cloud.ru Whisper API for transcribing your audio files.

How many languages does automatic language detection support for audio transcription?▼

Automatic language detection for audio transcription supports over 99 languages, allowing you to process diverse spoken content without needing to manually specify the language before conversion.

What is the maximum file size limit for transcribing audio recordings?▼

The maximum file size limit for transcribing audio recordings is 25 MB. Files exceeding this limit will need to be split or compressed before submitting them to the Cloud.ru Whisper API.

How do I prepare audio files for transcription if they are in an unsupported format?▼

To prepare unsupported audio files for transcription, you can use ffmpeg to normalize them into WAV format. The skill automates this normalization step for inputs like .ogg, .opus, .mp3, and .m4a.

Related Skills

Explore More Content & Communication Skills→
ratacatratacat
49

assemblyai-streaming

Stream audio via WebSocket for low-latency AssemblyAI speech-to-text transcription.

Community
Advanced
frumu-aifrumu-ai
114

meeting-notes

Analyze meeting transcripts to generate structured minutes, decisions, and action items.

Official
Intermediate
allenhutchisonallenhutchison
515

audio-transcription

Transcribe audio and video into structured Markdown notes in Obsidian.

Community
Intermediate
matthew-johnsonmatthew-johnson

whisper

Transcribe speech to text across 99 languages with Whisper models.

Community
Advanced