2noise/ChatTTS
ChatTTS is a generative text-to-speech model optimized for natural and expressive dialogue-based speech synthesis, supporting multi-speaker and fine-grained prosody control for conversational AI applications.
Awesome AI Agents › Audio & Voice Assistants
joinly-ai/joinly
joinly is connector middleware that gives an AI agent a seat in a video meeting. It runs a browser inside a Docker image, joins a call from its link on Google Meet, Zoom, Microsoft Teams or any other platform reachable through the web, and exposes meeting capabilities to agents as an MCP server, so tools for speaking, writing in the chat, reading the transcript and leaving the call become available to any MCP-capable client. Incoming audio is transcribed with a speech-to-text service and replies are spoken with text-to-speech; both layers are modular, with Whisper or Deepgram for recognition and Kokoro, ElevenLabs or Deepgram for synthesis. Built-in conversational logic handles turn taking, interruptions and multiple speakers so the agent does not talk over participants. The language model is supplied by the user and any provider works, including local models served through Ollama. Two deployment shapes are documented. The container can be run directly with a client flag, which starts a basic conversational agent and joins a meeting in one command, or it can run as a server on a port while an external client, distributed as the joinly-client package, connects to it. The external client accepts a JSON configuration listing further MCP servers, so tools such as web search, GitHub or Notion are added to the agent and can be used live during the call, which is what the demonstration videos show. The project is open source and self-hosted, with a managed cloud offered separately by the same team. It suits developers who want a meeting participant that acts on requests during a conversation rather than only producing notes afterwards.
https://github.com/joinly-ai/joinly
Also in Audio & Voice Assistants
neonbjb/tortoise-tts
Tortoise is a high-quality multi-voice text-to-speech system focused on realistic prosody and intonation, offering various usage modes and advanced performance optimizations.
livekit/agents
LiveKit Agents is an open-source framework for building real-time voice AI agents with integrated speech-to-text, large language models, text-to-speech, and telephony capabilities.
openinterpreter/01
01 is an open-source voice interface platform that enables natural language voice control across desktop, mobile, and ESP32 devices, offering extensive customization and hardware support.
ahmedeltaher/Android-MVVM-Architecture-Android-Voice-AI-SDK
A reusable Android library in Kotlin that adds a full voice conversation pipeline to an app, chaining microphone capture, voice activity detection, speech-to-text, an Anthropic Claude response and text-to-speech.
elevenlabs/ui
ElevenLabs UI is a component library built on shadcn/ui that provides customizable React components to help developers build multimodal agent and audio applications faster.
akdeb/ElatoAI
ElatoAI enables real-time AI speech interaction on Arduino ESP32 devices using OpenAI, Gemini, and Eleven Labs AI models with secure websocket communication and a web app for control.
bolna-ai/bolna
Bolna is an open-source end-to-end platform for building voice-first conversational AI agents by orchestrating telephony, speech recognition, language models, and speech synthesis technologies.