openai / openai-realtime-embeddedLinks
Instructions on how to use the Realtime API on Microcontrollers and Embedded Platforms
☆1,553Updated 2 months ago
Alternatives and similar repositories for openai-realtime-embedded
Users that are interested in openai-realtime-embedded are comparing it to the libraries listed below
Sorting:
- Realtime AI speech with OpenAI Realtime API on Arduino ESP32 with Secure Websockets and Deno edge functions with >15 minutes uninterrupte…☆1,009Updated this week
- The simplest and lowest-cost AI integration solution. If you like this project, please give it a Star~ | 最简单、最低成本的AI接入方案。喜欢本项目的话点个 Star 吧…☆705Updated this week
- Speech recognition☆941Updated 2 weeks ago
- 百聆 是一个类似GPT-4o的语音对话机器人，通过ASR+LLM+TTS实现，集成DeepSeek R1等优秀大模型，时延低至800ms，Mac等低配置也可运行，支持打断☆1,261Updated last week
- Build your own AI friend☆616Updated 4 months ago
- The ESP-BOX is a new generation AIoT development platform released by Espressif Systems.☆1,006Updated 3 months ago
- Have a natural, spoken conversation with AI!☆2,429Updated 3 weeks ago
- 本项目使用esp32、esp32s3接入Chatgpt、Claude、讯飞星火、豆包等15款大模型，实现语音对话聊天，支持语音唤醒、连续对话、音乐播放等功能，同时外接了一块显示屏实时显示对话的内容。☆415Updated 5 months ago
- Espressif intelligent voice assistant☆713Updated last week
- TTS with kokoro and onnx runtime☆2,019Updated 3 weeks ago
- 小智ESP32的Java企业级管理平台，提供设备监控、音色定制、角色切换和对话记录管理的前后端及服务端一体化解决方案☆458Updated this week
- first base model for full-duplex conversational audio☆1,747Updated 5 months ago
- ⚡ Insanely fast AI voice assistant with <500ms response times☆401Updated 6 months ago
- Omni SenseVoice: High-Speed Speech Recognition with words timestamps 🗣️🎯☆851Updated 3 months ago
- Xiaozhi MCP sample program☆78Updated 2 weeks ago
- Multi-modal OCR pipeline optimized for ML training (text, figure, math, tables, diagrams)☆647Updated 2 weeks ago
- RTC AIGC Demo☆147Updated last week
- Real-time conversational AI on ESP32-S3 using LiveKit, WebRTC and SenseCap Watcher☆103Updated 4 months ago
- ☆4,329Updated 2 months ago
- Inference code for the paper "Spirit-LM Interleaved Spoken and Written Language Model".☆908Updated 7 months ago
- Config files for self-hosting the FoloToy Community Server. Documents: https://docs.folotoy.com☆544Updated 6 months ago
- esp32 based device, mainly used for voice chat with large language models☆775Updated last year
- Desk-Emoji is a truly open-source AI desktop robot featuring an emoji screen, a two-axis console, and LLM capabilities for voice chat.☆451Updated 5 months ago
- ☆65Updated 6 months ago
- Dive is an open-source MCP Host Desktop Application that seamlessly integrates with any LLMs supporting function calling capabilities. ✨☆1,334Updated this week
- StreamSpeech is an “All in One” seamless model for offline and simultaneous speech recognition, speech translation and speech synthesis.☆1,088Updated 9 months ago
- Self-hosted voice chat with LLMs☆431Updated 3 months ago
- ☆222Updated 3 months ago
- Interface for OuteTTS models.☆1,294Updated last week
- TEN VAD: low-latency high-performance Voice Activity Detector☆477Updated this week