md-tts is a text-to-speech tool for technical Markdown with interactive pauses on code blocks.
Audio and Voice Recorder is a Windows app for recording high-quality audio for podcasts, meetings, lectures, and content creation.
interview-kit is an adaptive voice-interview engine for building voice agent applications.
morning-signal is an auto-generated daily briefing podcast using Claude AI, web search, and Polly TTS for listeners.
OSTT is an open source terminal-native speech-to-text tool for Linux and macOS with multiple provider support.
wakecore is an open hotword detection library for private voice systems.
muse-tts is a fully local TTS engine with 54 voices and 3 engines for AI voice synthesis.
Violin is an open-source video dubbing tool that translates videos into 33 languages with native-sounding voice-over and synced subtitles.
marmalade-tts is a unified local TTS command-line interface supporting multiple engines.
loxai provides real-time accent conversion for language learners using AI.
kokoro-mlx is a text-to-speech inference tool for Apple Silicon via MLX.
qwen3-asr-mlx is a speech-to-text inference tool for Apple Silicon via MLX.
lattice-asr is a hardware-adaptive multilingual ASR library with pluggable engines and streaming support.
ASSASMR is a mobile app providing ASMR audio content for relaxation.
Mumbli is a macOS app for local voice transcription using user-provided models.
timbregrid is an open compatibility and evaluation layer for open-source TTS.
Invoko is a desktop AI voice assistant that listens, remembers context, and performs tasks for users.
Vapi Blocks is a React and TailwindCSS UI library for adding Voice AI components to web applications.
Murf API provides AI voice generation and text-to-speech capabilities for integration into applications and workflows.
Sayna provides a unified voice and messaging layer integrating TTS, STT, and voice streaming for AI agents.
janus-remote is a Python voice-to-text bridge for Claude CLI on remote SSH sessions.

VoiceFleet is an AI voice receptionist for small businesses providing 24/7 call answering and booking.
localflow provides push-to-talk voice dictation for macOS users.
Simple-Type Audio Player is a desktop software for playing CDs and various music file formats on Windows.
meeting-asr is a CLI tool for Alibaba Cloud DashScope Fun-ASR video transcription.
voxn is a local voice note-taking suite for developers.

WhisperLink is a real-time voice communication app for clear speech in noisy environments.
Radyo Türk Live - Türkiye´nin en güzel radyolarında keyifle müzik dinlemeniz için hazırlanmış ücretsiz ve son…
Echocast is a mobile app providing voice recording and podcasting tools for users on Android devices.
signavis is a Python wrapper for SignaVis Player supporting HTML and Streamlit embedding.
mbrola is a speech synthesis system providing TTS capabilities via a Python package.

Giga provides real-time hallucination correction for voice agents with zero added latency.
Telora AI offers AI-powered voice agents for business to automate front desk and call handling.
AkoTao Cast is a Japanese app for high-quality AI text-to-speech voice generation.
audiobench is a web platform for audio benchmarking and analysis.
rapidtts is a Python library for text-to-speech synthesis.
Terms of Use for LS CTRL speaker controller.