Speech

A fully local, Spanish-language voice cloning and text-to-speech web application that turns a short recorded voice sample into speech reading any typed text, with no account, API or audio upload to a remote server.

• Speech

A curated, bilingual list of frameworks, tools and resources for building voice AI agents, covering voice activity detection, turn-taking, real-time speech recognition and speech synthesis.

• Speech
• Curated lists

A hands-free macOS voice loop for Claude Code that transcribes speech on-device, types it into the terminal window running Claude, and speaks the replies back in a chosen voice.

• Coding agents
• Speech

A Python library that runs text-to-speech, voice cloning and speech recognition entirely on Apple Silicon through Apple's MLX framework, sharing one Python API and command-line interface across several open speech models.

• Speech

A custom wake-word model for Home Assistant voice assistants, built with microWakeWord, that runs entirely on-device and comes with its full training pipeline so a user can train the same setup on any name of their own.

• Speech

An always-on, voice-controlled desktop agent that manages coding workspaces and background tasks, deciding when a progress update is worth interrupting the user for rather than narrating every step, with support for macOS, Windows and Ubuntu.

• Coding agents
• Speech

An unofficial C++ and GGML port of the CosyVoice text-to-speech inference pipeline, focused on CosyVoice3, with zero-shot, instruct and cross-lingual modes and streaming output.

• Speech

A local Russian speech-to-text engine written in Rust, built on the GigaAM v3 model and ONNX Runtime, usable as a command-line transcriber, an HTTP and WebSocket server, or an embedded library from several languages.

• Speech

A 559,000-parameter Japanese text-to-speech engine that runs in real time on a three-dollar ESP32-S3 microcontroller, doing morpheme analysis and pitch-accent estimation on the device with dependency-free C code, with a browser demo of the same engine compiled to WebAssembly.

• Speech

A fully offline, privacy-first voice assistant that combines a local mixture-of-experts language model, neural text-to-speech, real-time speech recognition and an audio codec in a C++ pipeline with no Python at runtime.

• Speech

An on-device speaker diarization engine from Picovoice that identifies distinct speakers and their speaking intervals in an audio recording, with SDKs for multiple languages and platforms.

• Speech

A dependency-free C inference engine that runs Qwen3-TTS text-to-speech models on the CPU using only a BLAS library, with support for nine voices and ten languages.

• Inference
• Speech

A survey and curated list of full-duplex spoken dialogue systems, the models and architectures that let a voice assistant listen and speak at the same time instead of taking strict conversational turns.

• Speech
• Papers

An on-device speech infrastructure library in C++17 for Linux, Windows and Android, providing voice activity detection, streaming speech-to-text, speaker diarization, text-to-speech and a voice-agent pipeline.

• Speech
• Libraries

A native streaming speech-recognition model that transcribes audio of unlimited length continuously, with a rolling key-value cache that keeps memory and latency bounded even in 24-hour operation.

• Speech

An on-device noise-suppression engine that removes background noise from audio entirely offline, with SDKs for Python, Android, iOS, C and the web across desktop, mobile and Raspberry Pi.

• Speech
• Libraries

ROS 2 packages that bring whisper.cpp speech-to-text and Silero voice-activity detection into a robot's software stack, so a robot can listen for and transcribe speech.

• Speech

A fully local voice AI app for iOS that runs speech-to-text, a language model and text-to-speech entirely on an iPhone's Neural Engine, GPU and CPU, with real-time conversation and no cloud calls after setup.

• Speech

CODEC is the open-source engine behind Sovereign AI Workstation, a voice-controlled AI agent for macOS that watches the screen, controls apps, writes code, and works as both an MCP client and an MCP server.

• Agent frameworks
• MCP servers
• Speech

A self-hostable, open-source voice agent operating system with a Rust runtime tuned for low latency, an AI-driven agent builder, and a Python control plane, meant as an alternative to managed voice AI platforms.

• Speech

A Docker image that runs a self-hosted Whisper speech-to-text server with an OpenAI-compatible transcription and translation API, optional speaker diarization, and GPU acceleration.

• Speech
• Containers

A bilingual, mental-model-first reference on audio machine learning, covering datasets, transformer architectures, speech recognition, text-to-speech, and production voice pipelines.

• Speech
• Books

A framework for training custom wake-word detection models, offering a range of neural network architectures suited to different devices from a Raspberry Pi Zero to a cloud server.

• Speech

A 25-language speech recognition model built from NVIDIA's Parakeet TDT 0.6B v3, replacing half its encoder's temporal filters with fitted, frozen Gabor kernels and retraining the rest, reporting lower error rates than Parakeet on most benchmarks.

• Models
• Speech