AI Speech Technologies

Local single-user AI chat application with configurable personas and TTS/STT integrations, using an OpenAI-compatible LLM server

a text-prompted genereative audio model

Self-hosted gateway for Xiaozhi-compatible voice devices; handles speech recognition and synthesis, routing requests to Claude Code or supported model APIs. Runs on macOS, Linux and Windows.

an open-source local voice agent pipeline combining VAD, STT, LLM, and TTS

Open source voice agent platform.

an on-device Apple Silicon voice agent for macOS that combines STT, local LLM inference, TTS, 38 local actions, and document RAG in a low-latency TUI/CLI.

An Asterisk-based AI voice agent project integrating telephony with voice AI workflows.

Open-source macOS dictation app that transcribes locally with Apple speech, NVIDIA Parakeet or Whisper; optional API connections are available. Requires macOS 14+; Apple Silicon recommended

Cross-platform SDK for on-device speech recognition (Voz) and speaker labeling (Who), plus audio enhancement and other speech models; Swift, Kotlin and JavaScript

a Swift package that integrates Whisper with Apple’s CoreML

ggml speech-to-text inference for 16+ model families

a ggml-based C++ inference port of NVIDIA NeMo Parakeet ASR models with streaming support

a family of models optimized for fast and accurate automatic speech recognition on resource-constrained devices. Designed to run efficiently on smaller hardware. The micro subdirectory contains the very-low-latency speech stack.

a real-time text-to-speech system based on Whisper

a distilled version of whisper that is 6 times faster

a general purpose speech recognition model

a C++ implementation of whisper that can run in consumer hardware

Android push-to-talk dictation app with on-device sherpa-onnx models or OpenAI cloud transcription; uses Accessibility to insert text into focused fields and falls back to the clipboard.

macOS daemon and menu bar app that watches Apple Voice Memos, transcribes them locally with Parakeet MLX, and writes structured Markdown notes

FastAPI server for Moonshine STT

A macOS dictation and transcription app that can use Apple’s speech stack as well as other local on-device engines, with optional prompt-driven post-processing.

a 100% local macOS hold-to-talk speech-to-text menu bar app with WhisperKit transcription and local LLM cleanup.

a Go-based local voice-to-text tool for Linux terminals that streams whisper.cpp transcription to stdout, files, or keystroke injection for dictating into focused terminal apps.

An offline, cross-platform speech-to-text app built with Tauri that transcribes locally. Uses Whisper and Parakeet models without sending audio to the cloud.

an editor for spoken-word audio with automatic transcription

An opinionated CLI for audio transcription

macOS app that transcribes podcasts and videos on-device, assigning each line to a speaker; built on Who and Apple’s speech transcriber

A cross-platform Whisper desktop app that works quite well on the Mac (including speaker diarization)

an open-source all-in-one recording transcription and diarization stack

A minimal, dependency-free C scaffold for Pocket-TTS, aimed at CPU-only TTS. Includes a tiny CLI in the flux2.c style.

Compact zero-shot voice cloning TTS models: the 0.6B Realistic Air release supports 23 languages; the 0.1B preview offers CPU inference via ONNX INT8 and has a separate model license.

A 7.88M-parameter English text-to-speech model distilled from Kokoro, with four voices and an 8.5 MB int8 ONNX model that runs on CPU.

Fish Audio text-to-speech MoE model with 35B parameters (3B active), voice cloning, natural-language control and multi-speaker generation

Multilingual zero-shot text-to-speech model and toolkit with voice cloning, voice design, pronunciation controls, and support for more than 600 languages

a lightweight text-to-speech model

Multi-language neural text-to-speech models

a lightweight text-to-speech model

a text-to-speech model that can generate expressive speech with a variety of styles and emotions.

an open-source text-to-speech system built on Llama-3b

a speech generation model from Sesame that generates RVQ audio codes from text and audio inputs.

a text-to-speech model designed specifically for dialogue scenarios, with decent prosody

a text-to-speech system built by inverting Whisper

a PyTorch implementation of a voice cloning model

A text to speech model that supports style diffusion

a detailed walkthrough of how to customize a voice model

Python CLI, stdin and HTTP server that gives LLM agents a cloned voice through an OmniVoice-compatible text-to-speech service

official PyTorch inference implementation for the Breeze TTS 2 English/Chinese text-to-speech model, with voice cloning and streaming

local text-to-speech server around Inflect Nano v2 with Speech Dispatcher integration

an open-source voice cloning studio with DAW-like features, local-first voice synthesis powered by Qwen3-TTS, multi-track timeline editor, and REST API

A lightweight text-to-speech (TTS) application designed to run efficiently on CPUs that supports voice cloning

a toolkit for doing speech processing and voice cloning

a tool for generating audiobooks from text using the Kokoro open weights model

a text-to-speech module that leverages the Microsoft Edge TTS API

a tool for generating podcasts from text

a tool that enables accurate voice cloning with multi-lingual support and flexible style control.

Real-time simultaneous Chinese–English speech translation model with inference and training tools; speech output and voice cloning require a configured TTS service.