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.
☆254Nov 24, 2025Updated 7 months ago
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. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Train and finutune text-to-speech models for Bengali and many other languages!☆18Apr 2, 2025Updated last year
- List of curated use cases built using Sesame's CSM 1B☆74May 29, 2025Updated last year
- Fine tuned llama 3 models for context based question answering in bengali language.☆18Oct 14, 2024Updated last year
- Fully Configurable RAG Pipeline for Bengali Language RAG Applications. Supports both Local and Huggingface Models, Built with Langchain.☆50Aug 16, 2024Updated last year
- Bangla TTS Inference pipeline using Vit TTS☆13Mar 24, 2024Updated 2 years ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- ☆18May 9, 2024Updated 2 years ago
- CUDA, CuDNN, NVIDIA Driver, and PyTorch Installation for Ubuntu☆12Feb 27, 2025Updated last year
- High-performance, semantic turn detection for conversational AI☆43Oct 1, 2025Updated 9 months ago
- ☆58Feb 8, 2026Updated 5 months ago
- Orpheus-TTS local speech synthesizer written entirely in C#☆31Nov 25, 2025Updated 7 months ago
- ☆15May 13, 2024Updated 2 years ago
- Bangla Unicode Normalization☆24May 26, 2024Updated 2 years ago
- ☆35Oct 23, 2025Updated 8 months ago
- Training code for kokoro tts model☆46Nov 15, 2025Updated 7 months ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- Bangla PDF to text converter that works on Windows, macOS, and Linux without any extra downloads or configurations.☆21Oct 12, 2024Updated last year
- ☆19Nov 30, 2024Updated last year
- A real-time voice chat application powered by local AI models☆137Apr 12, 2025Updated last year
- StyleTTS2 + Vocos as a Decoder☆13Mar 24, 2025Updated last year
- FastRTC voice agent☆22Mar 18, 2025Updated last year
- Text-audio foundation model from Boson AI☆118Sep 4, 2025Updated 10 months ago
- Docker image for Rerender A Video: Zero-Shot Text-Guided Video-to-Video Translation☆11Apr 14, 2024Updated 2 years ago
- A fourier-based audio-synthesiser wrote in MATLAB as a university project.☆11Jan 19, 2019Updated 7 years ago
- A Conversational Speech Generation Model☆14,683May 27, 2025Updated last year
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- Llama-Mimi is a speech language model that uses a unified tokenizer (Mimi) and a single Transformer decoder (Llama) to jointly model sequ…☆31Sep 20, 2025Updated 9 months ago
- Implementation of Sesame's Conversational Speech Model for Hugging Face Transformers☆58May 17, 2025Updated last year
- ☆54Dec 5, 2025Updated 7 months ago
- Towards Human-Sounding Speech☆6,221Dec 5, 2025Updated 7 months ago
- Official implementation of the TTS model Lina-Speech☆180Jan 9, 2025Updated last year
- Bring your code and propmpts easily to your LLM☆21Jun 10, 2025Updated last year
- LLMVoX: Autoregressive Streaming Text-to-Speech Model for Any LLM☆308May 16, 2025Updated last year
- Realtime demo, Streaming and Finetuning code for CSM☆454Sep 17, 2025Updated 9 months ago
- 🌼 Daisy-TTS: Simulating Wider Spectrum of Emotions via Prosody Embedding Decomposition☆14Nov 15, 2025Updated 7 months ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- This is a side project where me and my friend try to generate synthetic data in bangla from deepseek-r1. So that can be used for model di…☆11Jun 28, 2025Updated last year
- A generative speech model for daily dialogue.☆16Aug 21, 2025Updated 10 months ago
- Dockerized FastAPI wrapper for Kokoro-82M text-to-speech model w/multiplatform CPU, AMD, NVIDIA GPU PyTorch support, handling, and auto-s…☆5,094Jun 18, 2026Updated 3 weeks ago
- This comprehensive guide provides a universal process for preparing your own speech datasets and training a custom Text-to-Speech (TTS) m…☆35Updated this week
- Quickly create a Simli AI Agent☆21Feb 18, 2026Updated 4 months ago
- [ACL 2024] Generative Pre-Trained Speech Language Model with Efficient Hierarchical Transformer☆70Nov 1, 2024Updated last year
- Moshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audi…☆10,512May 16, 2026Updated last month