skills.rest
t-miura-024
t-miura-024COMMUNITY
Explore all skills by this author →
GitHub

mt-format-voice-input

Format raw voice transcription text with corrected punctuation and paragraph structure.

Updated May 15, 2026
Search Tags:#speech recognition#transcription#text formatting#punctuation#voice input#error correction
One-click install
npx skills add https://github.com/t-miura-024/tools --skill mt-format-voice-input
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: mt-format-voice-input
Source: https://github.com/t-miura-024/tools/tree/main/chezmoi/dot_config/opencode/skills/mt-format-voice-input
Command: npx skills add https://github.com/t-miura-024/tools --skill mt-format-voice-input

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill transforms raw voice-transcribed text into readable writing by fixing recognition errors, improving structure, and adding missing punctuation.

Core Features & Use Cases

  • Text Formatting: Inserts appropriate line breaks, paragraph divisions, and punctuation to make spoken text easier to read.
  • Recognition Correction: Uses known conversion history and context-based reasoning to repair speech-to-text mistakes and naming errors.
  • Use Case: Convert a voice memo or dictated note into polished text before passing it to another writing or productivity workflow.

Quick Start

Use the mt-format-voice-input skill to clean up the following voice transcription and return the corrected readable version.

Frequently Asked Questions about mt-format-voice-input

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

FAQPage Schema
How do I add punctuation and line breaks to raw voice transcription text?▼

Voice transcription text can be formatted into readable content by applying context-aware correction, paragraph formatting, and punctuation completion to fix missing punctuation and structure the text.

Can I fix speech recognition errors in dictated notes automatically?▼

Speech recognition errors in dictated notes are corrected using context-based reasoning and conversion history lookup to repair speech-to-text mistakes and naming errors during text formatting.

What is the best way to clean up voice memos before passing them to another workflow?▼

The best way to clean up voice memos for another workflow is to format raw transcription by correcting recognition errors, adding missing punctuation, and inserting paragraph divisions before passing the polished text to downstream tasks.

How does context-aware correction work for voice to text formatting?▼

Context-aware correction works by using surrounding text context and known conversion history to identify and repair speech-to-text mistakes, completing missing punctuation and structuring paragraphs for readable output.

Does voice input formatting report what changes were applied to the transcription?▼

Voice input formatting includes reporting of applied changes, allowing users to see exactly which recognition corrections, punctuation additions, and paragraph formatting adjustments were made to the original text.

Related Skills

Explore More Content & Communication Skills→
lvhuanidlvhuanid

ASR

Transcribe spoken audio into written text using the z-ai-web-dev-sdk.

Community
Intermediate
haryelramalhoharyelramalho

humanizer

Detect and rewrite AI-generated writing patterns into natural human voice.

Community
Intermediate
NourcineAbNourcineAb

stream-chain

Orchestrate sequential AI workflows by chaining prompts and transforming outputs across processing steps.

Community
Advanced
GitnappGitnapp

whisper

Transcribe spoken audio into text with timestamps using Whisper.

Community
Advanced