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
bolna-ai/bolna
Bolna is an end-to-end open-source platform designed to build voice-first conversational AI agents quickly and efficiently. It provides a comprehensive orchestration framework that integrates Automatic Speech Recognition (ASR), Large Language Models (LLMs), and Text-to-Speech (TTS) technologies to enable seamless voice-driven interactions. The platform supports multiple telephony providers such as Twilio and Plivo for initiating phone calls, and it can transcribe conversations using providers like Deepgram. Bolna leverages various LLMs including OpenAI, DeepSeek, Llama, Cohere, and Mistral to handle conversational logic and generate responses. These responses can then be synthesized back into speech using TTS providers like AWS Polly, ElevenLabs, OpenAI, Azure, and others. The repository contains the core orchestration platform that manages voice conversations over websockets, enabling developers to create AI voice agents that can perform tasks through conversational instructions defined in JSON. Bolna also offers hosted APIs and a no-code UI playground, although these components are currently closed source. The development philosophy emphasizes that all new integrations and features first land in the open-source package, which forms the backbone for the hosted services and UI. Bolna supports a local development setup using Docker containers, including telephony servers, the Bolna server, ngrok for tunneling, and Redis for data persistence. Users can configure their environment with API keys for various providers to customize their voice AI applications. The platform is actively maintained with community involvement encouraged, and it aims to facilitate the adoption of voice AI technologies by providing a flexible, extensible, and production-ready framework. Overall, Bolna is a powerful tool for developers and organizations looking to build sophisticated voice AI agents that integrate multiple speech and language technologies, telephony services, and cloud providers in a unified, open-source solution.
https://github.com/bolna-ai/bolna
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.
joinly-ai/joinly
joinly is a self-hosted MCP server that lets an AI agent join Google Meet, Zoom or Teams calls in a browser, listen through speech-to-text and reply by voice or chat in real time.