Speech

Rapida is an open-source voice AI orchestration platform for building real-time conversational voice agents, combining audio streaming, speech-to-text, text-to-speech, voice activity detection, multi-channel integration and observability.

• Speech

A real-time voice assistant built around a small, open-weight text-to-speech model that keeps the whole spoken conversation, including the caller's own audio, in context so replies carry natural prosody across turns.

• Speech

An open-source orchestration platform for building voice-driven conversational AI applications, connecting telephony, speech recognition, language models and speech synthesis providers over websockets.

• Speech

A voice assistant that talks through a project idea with the user, writes the resulting design to a file, then starts and supervises a real Claude Code session on it, announcing out loud when the agent needs input.

• Coding agents
• Speech

A modular Swift SDK for running text-to-speech, speech-to-text, voice activity detection, and speech-to-speech models on Apple Silicon through MLX, with importable modules for just the models an app needs.

• Speech
• Libraries

A multilingual, zero-shot text-to-speech system that clones a voice from a short reference clip and speaks any of fourteen supported languages in that voice, without needing a matching transcript.

• Speech

A pure Rust implementation of Mistral's Voxtral Mini 4B speech recognition and text-to-speech models, running natively or in the browser through the Burn machine-learning framework.

• Speech

A serving framework for audio and multimodal AI models that runs text-to-speech, speech recognition, and omni chat models behind an OpenAI-compatible API, built to handle multi-stage generation pipelines.

• Inference
• Speech

Optimized, open-weight Whisper speech-to-text models with streaming inference engines for NVIDIA GPUs and on-device Apple Silicon, aimed at low-latency real-time transcription.

• Inference
• Speech

An implementation of Nvidia's Parakeet automatic speech recognition models for Apple Silicon using MLX, with a command-line transcription tool.

• Speech

Tel-Agent is a self-hosted, open-source gateway connecting an existing phone line to an AI agent over SIP, checking each caller against routing rules before passing the call to a person, blocking it, or handing it to an agent that can transfer calls and take messages.

• Speech

Patter is an open-source SDK that gives an AI agent a phone number, handling the agent loop, speech-to-text, text-to-speech, real-time voice and the telephony carrier in one Python or TypeScript API so a developer can swap any provider in that stack with one line.

• Speech

MiMo-Audio is an audio language model trained on more than one hundred million hours of audio that shows few-shot generalization across audio tasks it was not explicitly trained for, such as voice conversion, style transfer and speech editing.

• Speech
• Generative media

An open-source collection of on-device speech AI models for Apple Silicon, covering speech recognition, synthesis, speech-to-speech, voice activity detection, and speaker diarization.

• Speech

A JavaScript SDK that runs large language models, speech recognition, text-to-speech and audio separation directly inside the browser using WebGPU, with no server required.

• Inference
• Speech

A system that gives a text-based LLM a voice by wrapping it with low-latency speech-to-text and text-to-speech models, so a user can talk to it out loud.

• Speech

A family of end-to-end speech recognition models from Tongyi Lab, covering many languages and Chinese regional dialects and accents, deployable through Transformers, FunASR, vLLM or llama.cpp.

• Speech

The official MiniMax Model Context Protocol server that lets Claude Desktop, Cursor, Windsurf and other MCP clients generate speech, clone voices, and generate images and video.

• MCP servers
• Speech
• Generative media

A macOS CLI for on-device speech transcription using Apple's Speech framework, producing SRT/VTT/JSON captions from files, transcribing live system audio and microphone input, and exposing an MCP server for agents.

• Speech

A C/C++ speech-to-text inference library that runs 16 model families and more than 60 model variants on the ggml runtime, with Metal, Vulkan and CUDA GPU backends plus an accelerated CPU path.

• Speech

A research-preview, fully on-device real-time multimodal voice assistant with features similar to OpenAI's GPT-Live, using hands-free turn-taking detection and sentence-by-sentence streamed replies, with an optional cloud research step.

• Speech

A roughly 0.1-billion-parameter end-to-end omni model, trained entirely from scratch, that takes text, speech, and image input and produces text and streaming speech output.

• Models
• Speech

A realtime voice runtime that keeps an AI agent conversing naturally by voice while it works, so it can keep talking, thinking, and calling tools without breaking the conversation.

• Speech

An open-source meeting-transcription platform whose bot joins Google Meet, Microsoft Teams, and Zoom calls and streams real-time, speaker-attributed transcripts that agents can turn into a shared knowledge base.

• Speech