Voice Apps Index

Master Index

Index of voice typing, dictation, and speech-to-text applications and utilities.

In Development

VoiceType

A fork of Deepgram's Linux starter with CLI-to-GUI conversion, hotkey support, API key editing, and cost tracking. Uses Deepgram streaming ASR.

View Repo

Parakeet Type Ubuntu

On-device voice typing for Linux using Parakeet and NeMo ASR models via sherpa-onnx. Built-in punctuation, multiple model profiles, system tray app with configurable hotkeys. No cloud, no GPU required.

View Repo

AI Typer V2

Voice dictation with multimodal AI cleanup — speak naturally, get polished text. Uses Gemini multimodal audio processing.

View Repo

Wayland Voice Typer

Simple GUI around whisper.cpp for voice-to-text on Linux.

View Repo

Quick STT

Optimised always-on STT for Ubuntu with ROCm support.

View Repo

hyprvoice

Voice-powered typing for Wayland/Hyprland desktops.

View Repo

Mooshine Dictation App

Moonshine-based dictation application.

View Repo

Local STT App

Local speech-to-text application.

View Repo

Voice Typing 1125

Voice typing application iteration.

View Repo

Old Iterations

AI Transcription Notepad

Voice note-taking utility that uses cloud audio multimodal models for single-pass transcription and text cleanup.

View Repo

Thought Pad

Linux desktop application providing a two-stage process for creating notes from dictated speech — transcription via Whisper API followed by light text formatting. Exports to markdown docs.

View Repo

Whisper Typer 0911

Earlier Whisper-based voice typing iteration.

View Repo

Deepgram Voice Keyboard Ubuntu

WIP STT utility using cloud STT APIs on Ubuntu.

View Repo

Voiceflow V1

Early voice flow implementation.

View Repo

Voiceflow Dev

Voice flow development iteration.

View Repo

Voice Flow Idea Dev

Voice flow idea development workspace.

View Repo

Whisper Typing Linux 1125

Whisper-based typing tool for Linux.

View Repo

Voice Keyboard

Voice keyboard application.

View Repo

Android Voice Keyboard

Voice keyboard for Android.

View Repo

Voice Notepad Android

Android fork of transcription UI.

View Repo

Transcription Tools

Gemini Audio Transcriber

File upload based multimodal transcription tool using Gemini via Open Router.

View Repo

Gemini Transcription Notepad

Gemini-powered transcription notepad with cleanup.

View Repo

Gemini ASR Transcriber

Transcription notepad for Gemini ASR.

View Repo

DVR Transcriber

Workflow workspace for importing recordings from a DVR and using AI for transcription.

View Repo

Transcript Creator

Audio cleanup and transcription tool.

View Repo

Local Multimodal Transcriber

Local transcription app with audio multimodal design.

View Repo

ASR Transcription Pipeline

ASR transcription pipeline.

View Repo

Transcription MCPs

Gemini Transcription MCP

MCP server for Gemini multimodal audio transcription with built-in post-processing.

View Repo

Cloud ASR MCP

MCP for using various cloud ASR models for speech-to-text and transcription.

View Repo

Local AI Transcription MCP

MCP for local AI transcription.

View Repo

Local Transcription MCP

WIP MCP for local STT with cleanup on AMD GPU machines.

View Repo

OR Audio Transcription MCP

Open Router-based audio transcription MCP server.

View Repo

Evaluations & Benchmarks

Whisper Fine Tune Accuracy Eval

Comparing Whisper fine-tunes versus stock Whisper on local inference.

View Repo

Whisper WPM Background Noise Eval

Quick eval to answer: how much does speaking pace affect WER/accuracy in ASR?

View Repo

Transcription Cleanup Eval

Evaluating various cloud audio understanding models on the transcribe-and-cleanup workflow.

View Repo

One Shot Transcription Microphone Eval

Test samples for various microphones with an STT accuracy evaluation.

View Repo

Local ASR STT Benchmark

Quick evaluation to find the best STT model in Speech Note (Ubuntu) for local hardware.

View Repo

Whisper WPM Test

Whisper words-per-minute testing.

View Repo

Gemini 3.1 Lite Audio Understanding Eval

Evaluation of Gemini 3.1 Lite on audio understanding tasks.

View Repo

Voice Cleanup Prompt Experiment

Testing various permutations in system prompting for raw audio transcript cleanup and comparing multimodal ASR vs. the STT + LLM approach.

View Repo

Whisper Fine-Tuning & Setup

Whisper Finetune V2

Whisper fine-tuning iteration.

View Repo

Modal Whisper Finetune Script

Validated fine-tuning script for fine-tuning Whisper on Modal GPU with a preformatted audio dataset.

View Repo

Whisper Fine Tuning Data

Whisper fine-tuning dataset.

View Repo

Whisper Fine Tune 171125

Whisper fine-tuning iteration.

View Repo

Whisper Base FUTO

Whisper base model via FUTO.

View Repo

Local STT Fine Tune Tests

Local STT fine-tuning tests.

View Repo

Fine Tuned STT Formats

Fine-tuned STT data formats.

View Repo

whisper-wayland-rocm

Whisper-Wayland with ROCm GPU acceleration — Docker setup for AMD GPUs.

View Repo

whisper-cpp-rocm-setup

whisper.cpp ROCm setup scripts.

View Repo

Whisper Local Notes

Notes on local Whisper usage.

View Repo

ASR Training Data

ASR Training Data Collector

GUI to facilitate gathering training data for ASR/STT apps in organised datasets with audio capture, text capture, and JSONL metadata construction. Supports LLM-generated text and user-provided.

View Repo

ASR Training Data Collector GUI Template

GUI template for ASR training data collection.

View Repo

ASR Training Data Chunker

Breaks up texts by approximate reading duration for ASR training.

View Repo

Other Utilities

Voice Note Recorder Ubuntu

GUI for recording voice notes on Ubuntu/Linux.

View Repo

Readiness Voice Agent

Voice agent implementation for readiness checklists.

View Repo

Voice Note Classification Model

Model for classifying voice notes.

View Repo

Voice Note Classifier Model

Voice note classifier model.

View Repo

Voice Note Dataset

Frontend for open source voice note dataset for annotation/classification project.

View Repo

Voice Note Ragie Pipeline

Test pipeline: voice context data to Ragie.

View Repo

Voice Prompt Cleanup Script

Audio processing cleanup script.

View Repo

Transcription Macropad

Macropad configuration for transcription workflows.

View Repo

Dictation Macropad

Plan/key allocation for a macropad optimised for heavy daily dictation workflows.

View Repo

Voicepad

Planning notes for a macropad for STT users.

View Repo

Voice Typer HW

Voice typer hardware notes.

View Repo

Voice Headset Design

Voice headset design notes.

View Repo

Dictation Microphones

Dictation microphone notes and comparisons.

View Repo

speech-notes-with-text-fixes

Speech Note Linux app with text fixes — note taking, reading and translating with offline STT, TTS, and machine translation.

View Repo

Hebrish Whisper Tester

Testing Whisper with Hebrew-English mixed speech.

View Repo

Notes & Ideas

VoiceBox

Concept for a speech tech solution — specced out by Claude.

View Repo

Linux Realtime Voice Typing

Planning and research for real-time voice typing on Linux (Deepgram, Gemini, Parakeet).

View Repo

Linux Voice Typing App Notes

Planning notes for a Linux voice typing tool.

View Repo

Speech To Text Chain Notes

Notes on STT processing chain for future voice projects.

View Repo

Cloud STT Price Points

Point-in-time pricing snapshots for ASR services.

View Repo

ASR And STT AI Notebook

Prompts and outputs on STT, ASR, and fine-tuning with Claude.

View Repo

Linux Friendly Voice Tech

List of resources for voice technology with Linux support, encompassing STT, ASR, and dev frameworks.

View Repo

Voice Control Linux

Claude-enhanced research for voice control platforms with Linux support.

View Repo

voice-typing-collection

Collection of voice typing / STT GitHub repos for testing on Linux.

View Repo

Awesome Whisper Apps

Useful speech-to-text tools that use Whisper under the hood (API/local).

View Repo

Voiceflow Planner

Voiceflow planning notes.

View Repo

STT TTS Train 1125

STT and TTS training notes.

View Repo