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
ahmedeltaher/Android-MVVM-Architecture-Android-Voice-AI-SDK
The Android Voice AI SDK is a Kotlin library, structured according to the model-view-viewmodel pattern, that gives an Android application a complete voice-driven conversation pipeline through a single builder call. The flow runs from the device microphone through AudioRecord, voice activity detection and speech-to-text, sends the transcript to Anthropic Claude for a response, and speaks the reply back through text-to-speech. Speech recognition and synthesis engines are swappable adapters: the recognition side supports the Android SpeechRecognizer and OpenAI Whisper, while synthesis supports the Android TextToSpeech engine and ElevenLabs. The documented capability layers cover audio input with voice activity detection, noise handling and streaming PCM capture; recognition with language detection and speaker diarization; understanding with intent extraction, entity recognition and conversation context; action with API orchestration, workflow execution and task automation; response generation by the language model; voice output with style selection and audio streaming; safety features including user consent, authentication and abuse prevention; and analytics covering conversation logs, session summaries and quality metrics. Security utilities include redaction of personally identifiable information and encrypted key storage, and the setup instructions keep the Anthropic API key in a git-ignored local.properties file exposed through BuildConfig. Ready-made Jetpack Compose components ship with the library: a permission gate composable that handles the RECORD_AUDIO runtime permission, a voice button bound to the session, and a conversation view rendering the message list from a view model. Dependency injection is wired with Hilt, though the SDK can also be constructed directly, and the session object is started explicitly. The project targets minimum SDK 24, uses Kotlin 2.0 or newer with coroutines, and is tested with MockK, JUnit 5 and Espresso. It is aimed at Android developers adding conversational voice features to an existing app.
https://github.com/ahmedeltaher/Android-MVVM-Architecture-Android-Voice-AI-SDK
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.
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.
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.