asiff00 / On-Device-Speech-to-Speech-Conversational-AI
This is an on-CPU real-time conversational system for two-way speech communication with AI models, utilizing a continuous streaming architecture for fluid conversations with immediate responses and natural interruption handling.
☆114Updated last week
Alternatives and similar repositories for On-Device-Speech-to-Speech-Conversational-AI:
Users that are interested in On-Device-Speech-to-Speech-Conversational-AI are comparing it to the libraries listed below
- LLMVoX: Autoregressive Streaming Text-to-Speech Model for Any LLM☆240Updated last month
- Streaming and Finetuning code for CSM☆239Updated last week
- Sesame Converse - Real Time Conversations - Powered by Gemma 3☆61Updated last month
- High-performance Text-to-Speech server with OpenAI-compatible API, 8 voices, emotion tags, and modern web UI. Optimized for RTX GPUs.☆277Updated last week
- Examples of using the llasa-tts models locally☆163Updated this week
- Speech-to-speech AI assistant with natural conversation flow, mid-speech interruption, vision capabilities and AI-initiated follow-ups. F…☆100Updated last week
- Run Orpheus 3B Locally With LM Studio☆379Updated last month
- OpenAI compatible TTS for Sesame CSM:1b & dia:1.6b - Voice Cloning from File/YT☆294Updated this week
- Implementation of Sesame's Conversational Speech Model for Hugging Face Transformers☆45Updated 2 weeks ago
- Simulates talk with an AI that can express emotions☆65Updated 9 months ago
- G2P☆218Updated last week
- API server for Instant voice cloning by MyShell.☆89Updated 7 months ago
- LLaSA: Scaling Train-time and Inference-time Compute for LLaMA-based Speech Synthesis☆516Updated 2 weeks ago
- ☆95Updated 11 months ago
- List of curated use cases built using Sesame's CSM 1B☆62Updated last month
- A real-time speech-to-speech chatbot powered by Whisper Small, Llama 3.2, and Kokoro-82M.☆221Updated 3 months ago
- ☆63Updated last month
- ☆216Updated last month
- Official code for "F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching"☆44Updated 4 months ago
- Official code for "F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching"☆77Updated 6 months ago
- Unlock Pose Diversity: Accurate and Efficient Implicit Keypoint-based Spatiotemporal Diffusion for Audio-driven Talking Portrait☆244Updated this week
- A TTS model capable of generating ultra-realistic dialogue in one pass.☆75Updated this week
- A Conversational Speech Generation Model☆11Updated last month
- Automatically cleaning, enhancing, segmenting, filtering, and formatting a dataset to fine tune or train a voice model.☆35Updated this week
- A cutting-edge Cascading voice assistant combining real-time speech recognition, AI reasoning, and neural text-to-speech capabilities.☆58Updated 2 weeks ago
- Real-time Voice Activity Detection (VAD) with some example use case like simple voice bot and live transcription (realtime transcription)☆77Updated 10 months ago
- Speech To Speech: an effort for an open-sourced and modular GPT4-o☆53Updated 6 months ago
- ☆130Updated 4 months ago
- Sesame CSM 1B Voice Cloning☆280Updated last month
- Lightweight Gradio based WebUI for orpheusTTS - WSL / Linux [CUDA]☆87Updated last month