KoljaB / LocalAIVoiceChat
Local AI talk with a custom voice based on Zephyr 7B model. Uses RealtimeSTT with faster_whisper for transcription and RealtimeTTS with Coqui XTTS for synthesis.
☆628Updated 8 months ago
Alternatives and similar repositories for LocalAIVoiceChat:
Users that are interested in LocalAIVoiceChat are comparing it to the libraries listed below
- Command Your World with Voice☆659Updated 4 months ago
- AlwaysReddy is a LLM voice assistant that is always just a hotkey away.☆736Updated 2 months ago
- A simple FastAPI Server to run XTTSv2☆504Updated 9 months ago
- Webui for using XTTS and for finetuning it☆790Updated 3 months ago
- Local SRT/LLM/TTS Voicechat☆667Updated 6 months ago
- ☆326Updated 10 months ago
- Local voice chatbot for engaging conversations, powered by Ollama, Hugging Face Transformers, and Coqui TTS Toolkit☆763Updated 8 months ago
- A modular voice assistant application for experimenting with state-of-the-art transcription, response generation, and text-to-speech mode…☆970Updated 2 weeks ago
- Amica is an open source interface for interactive communication with 3D characters with voice synthesis and speech recognition.☆944Updated this week
- Slightly improved official version for finetune xtts☆336Updated last month
- Low latency ai companion voice talk in 60 lines of code using faster_whisper and elevenlabs input streaming☆281Updated 10 months ago
- Converts text to speech in realtime☆2,942Updated 2 weeks ago
- Simulates talk with an AI that can express emotions☆67Updated 9 months ago
- AllTalk is based on the Coqui TTS engine, similar to the Coqui_tts extension for Text generation webUI, however supports a variety of adv…☆1,740Updated last week
- An OpenAI API compatible text to speech server using Coqui AI's xtts_v2 and/or piper tts as the backend.☆752Updated 3 months ago
- Like ChatGPT's voice conversations with an AI, but entirely offline/private/trade-secret-friendly, using local AI models such as LLama 2 …☆158Updated 8 months ago
- High-performance Text-to-Speech server with OpenAI-compatible API, 8 voices, emotion tags, and modern web UI. Optimized for RTX GPUs.☆324Updated 2 weeks ago
- ☆1,126Updated 2 months ago
- Interface for OuteTTS models.☆1,205Updated this week
- ☆96Updated last year
- ☆1,766Updated this week
- A User Interface for XTTS-2 Text-Based Voice Cloning using only 10 seconds of speech☆340Updated 4 months ago
- A talking LLM that runs on your own computer without needing the internet.☆452Updated 8 months ago
- WhisperFusion builds upon the capabilities of WhisperLive and WhisperSpeech to provide a seamless conversations with an AI.☆1,598Updated 9 months ago
- Mac compatible Ollama Voice☆479Updated last year
- Implementation of F5-TTS in MLX☆525Updated last month
- A webui for different audio related Neural Networks☆1,160Updated 8 months ago
- ☆223Updated last month
- ☆483Updated 11 months ago
- The code for the bark-voicecloning model. Training and inference.☆696Updated last year