Speech

A private AI assistant and local runtime that runs entirely on the user's own hardware: it holds conversations by voice or text, controls the desktop, reads the screen, writes code, and builds a private model of the user over time.

• Agent frameworks
• Agent memory
• Speech

A fully local, full-duplex voice assistant for Windows that lets a user interrupt it mid-sentence and answers using visual context captured from the desktop the instant the user speaks.

• Speech

A cross-platform desktop application for transcribing audio and video offline using OpenAI's Whisper models on the user's own machine, with an optional OpenAI backend when a user supplies an API key.

• Speech

An open-source voice assistant that runs on your own computer and your own OpenAI key: you talk to it, and a background team of AI bots handles slower work in a real browser, a shell and your files while the voice call keeps talking.

• Agent frameworks
• Speech

Pre-compiled, encrypted streaming speech-recognition model weights in VoxRT's .vxrt format, for consumption by the VoxRT on-device runtime on Android and iOS.

• Models
• Speech

A command-line tool that transcribes and summarizes local audio or video files or YouTube content entirely on Apple Silicon using MLX, picking Voxtral or Whisper for transcription and a Qwen3 model for summarization based on the Mac's available memory.

• Inference
• Speech

A local web chat interface that connects LM Studio and other OpenAI-compatible model providers to an in-app tool runtime and the Supertonic text-to-speech engine, with hybrid memory search across conversations.

• Inference
• Speech

Adds hotword-biased decoding to the WeNet C++ speech recognition runtime, using fuzzy phoneme matching and an automatic multi-objective tuner.

• Speech

An Apache-2.0 toolkit for training a custom wake word and running it fully on-device in Python, the browser, or on iOS and Android.

• Speech

A Swift package for streaming, on-device speech recognition on iOS, built on a custom Rust inference runtime (VoxRT) rather than ONNX Runtime or PyTorch Mobile, running a 32-million-parameter FastConformer model with roughly 90ms per-chunk latency on an iPhone 13 Pro Max.

• Speech
• Mobile

A cross-platform desktop app that adds a voice interface to coding agents such as Claude Code, Cursor, Codex and Gemini CLI: you talk to the agent out loud and hear its answers in a natural voice, with everything running on the local machine.

• Coding agents
• Speech

A family of three Arabic-first, zero-shot text-to-speech models that clone a voice from a short reference clip, support inline expression tags, and speak Modern Standard and several dialectal forms of Arabic as well as English.

• Speech

A full-duplex voice plugin for DeepSeek Harness that streams speech recognition into an editable draft as you talk, reads replies aloud sentence by sentence with live captions, and lets you interrupt playback just by speaking.

• Agent skills
• Speech

A free hook that speaks a short summary out loud after your coding agent finishes a reply, using a local ONNX text-to-speech model with no cloud API, API key, or subscription.

• Agent skills
• Speech

A companion toolkit that adds LoRA fine-tuning to CosyVoice v3 for single-speaker voice cloning on one consumer GPU, since the upstream code only supports full fine-tuning.

• Models
• Speech

An unofficial Mandarin Chinese fine-tune of the Supertonic-3 on-device text-to-speech model, distributed as optimized ONNX graphs with streaming synthesis and Chinese-specific text normalization for dates, money and phone numbers.

• Speech

An Android library for streaming, on-device speech recognition, built on a custom Rust inference runtime and a 32M-parameter NeMo FastConformer model.

• Speech
• Mobile

A C++ and GGUF reimplementation of the Breeze-TTS-2 bilingual English and Mandarin text-to-speech model, supporting voice design, cloning, direction, and experimental voice conversion with a Vulkan backend.

• Inference
• Speech

A dependency-free C and SIMD int8 runtime that runs the FastEnhancer-Medium speech enhancement model in real time, without an inference framework or heap allocation after startup.

• Speech
• Libraries

A self-hosted text-to-speech engine with 28 voices in ten languages and voice cloning from about ten seconds of audio, with native SDKs for Python, Swift, Go, Rust and TypeScript, running offline after the first model download.

• Speech

A CLI-first tool for running and serving automatic speech recognition models locally, with a Ryzen AI NPU backend as well as CPU and GPU, for developers integrating local speech recognition into their own apps.

• Speech

A proof-of-concept Android app demonstrating the KeenASR speech-recognition SDK, showing how to build a language model and decoding graph from a chosen set of phrases and run on-device speech recognition against it.

• Speech

A Docker image for a self-hosted, real-time speech-to-text server based on faster-whisper, offering WebSocket streaming transcription and an OpenAI-compatible REST API, with optional GPU acceleration.

• Speech
• Containers

A toolkit that generates realistic multi-speaker meeting audio from room-impulse-response simulation and HMM-based turn-taking models, producing per-speaker reference signals for training speech separation, enhancement and diarization systems.

• Speech