speech-to-text

Transcribe audio files into text with timestamps using Whisper models.

688|95|Updated Jan 31, 2026

Search Tags:#translation #transcription #whisper #audio #stt #speech to text

Ready to run

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

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: speech-to-text
Source: https://github.com/inference-sh/skills/tree/main/tools/audio/speech-to-text
Command: npx skills add https://github.com/inference-sh/skills --skill speech-to-text-inference-sh

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

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

Core Features & Use Cases

Transcription: Convert audio files into text transcripts.
Translation: Translate spoken audio from various languages into English.
Timestamps: Generate time-coded segments for precise referencing.
Use Case: Transcribe a lengthy meeting recording to quickly generate minutes or create subtitles for a video by extracting dialogue.

Quick Start

Use the speech-to-text skill to transcribe the audio file located at https://meeting.mp3.

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 an audio file to text with timestamps?▼

To transcribe audio to text with timestamps, you can use speech recognition models like Fast Whisper or Whisper V3. The transcription process automatically generates time-coded segments for precise referencing within the audio file.

Can I translate spoken audio from another language to English?▼

Yes, you can translate spoken audio from various languages to English. The speech-to-text transcription supports multi-language audio recognition and directly translates the spoken dialogue into written English text.

What is the best way to generate subtitles or meeting minutes from a recording?▼

The best way to generate subtitles or meeting minutes is to transcribe the recording using speech recognition. This converts the spoken dialogue into searchable, editable text with detailed timestamps for quick referencing.

Does speech to text transcription work for podcast transcripts and voice notes?▼

Yes, speech to text transcription works for podcast transcripts and voice notes. It converts audio files into written text transcripts, making the audio content searchable and editable for various content creation use cases.

Do I need to install Whisper V3 locally to transcribe an mp3 file?▼

No, you do not need to install Whisper V3 locally to transcribe an mp3 file. You can reference your audio file via a URL, and the transcription service will process the audio remotely using advanced speech recognition models.