pipecat-ai / pipecatLinks
Open Source framework for voice and multimodal conversational AI
β8,410Updated this week
Alternatives and similar repositories for pipecat
Users that are interested in pipecat are comparing it to the libraries listed below
Sorting:
- A fast multimodal LLM for real-time voiceβ4,226Updated last month
- A powerful framework for building realtime voice AI agents π€ποΈπΉβ7,888Updated this week
- Fast and accurate automatic speech recognition (ASR) for edge devicesβ2,918Updated this week
- Local realtime voice AIβ2,373Updated 7 months ago
- π€ Build voice-based LLM agents. Modular + open source.β3,591Updated 11 months ago
- Speech To Speech: an effort for an open-sourced and modular GPT4-oβ4,209Updated 6 months ago
- first base model for full-duplex conversational audioβ1,766Updated 9 months ago
- Towards Human-Sounding Speechβ5,649Updated 5 months ago
- Moshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audiβ¦β8,999Updated last week
- The python library for real-time communicationβ4,355Updated last month
- LLaMA-Omni is a low-latency and high-quality end-to-end speech interaction model built upon Llama-3.1-8B-Instruct, aiming to achieve speeβ¦β3,079Updated 5 months ago
- Converts text to speech in realtimeβ3,578Updated 3 months ago
- β982Updated last month
- Inference and training library for high-quality TTS models.β5,452Updated 10 months ago
- The data plane for agents. Arch is a models-native proxy server that handles the plumbing work in AI: agent routing & hand off, guardrailβ¦β4,071Updated last week
- A TTS model capable of generating ultra-realistic dialogue in one pass.β18,627Updated 3 months ago
- A framework for serving and evaluating LLM routers - save LLM costs without compromising qualityβ4,347Updated last year
- An Open Source text-to-speech system built by inverting Whisper.β4,506Updated 4 months ago
- React app for inspecting, building and debugging with the Realtime APIβ3,483Updated last month
- WhisperFusion builds upon the capabilities of WhisperLive and WhisperSpeech to provide a seamless conversations with an AI.β1,632Updated last year
- Have a natural, spoken conversation with AI!β3,262Updated 3 months ago
- Dockerized FastAPI wrapper for Kokoro-82M text-to-speech model w/CPU ONNX and NVIDIA GPU PyTorch support, handling, and auto-stitchingβ3,823Updated 2 weeks ago
- A react-based starter app for using the Live API over websockets with Geminiβ2,360Updated last week
- Python & JS/TS SDK for running AI-generated code/code interpreting in your AI appβ2,026Updated this week
- Foundational model for human-like, expressive TTSβ4,187Updated last year
- The open-source LLMOps platform: prompt playground, prompt management, LLM evaluation, and LLM observability all in one place.β3,254Updated this week
- β2,491Updated this week
- π§ Open source LLM observability platform. One line of code to monitor, evaluate, and experiment. YC W23 πβ4,612Updated this week
- Kyutai's Speech-To-Text and Text-To-Speech models based on the Delayed Streams Modeling framework.β2,468Updated last month
- https://hf.co/hexgrad/Kokoro-82Mβ4,577Updated 2 months ago