Run a <400ms latency Voice Agent on just 4GB VRAM. Fully offline, no API keys required. Optimized for GTX 1650 and edge robotics with zero-copy inference. (Apache 2.0)
-
Updated
May 24, 2026 - Python
Run a <400ms latency Voice Agent on just 4GB VRAM. Fully offline, no API keys required. Optimized for GTX 1650 and edge robotics with zero-copy inference. (Apache 2.0)
Dum dictation is a local, open-source dictation tool primarily for Mac. It gets technical vocabulary right and offers a responsive word-by-word feel directly at your cursor.
本地优先 AI 语音输入工具 | Local-first AI voice typing tool. 支持 Whisper/SenseVoice/Parakeet/Qwen asr,离线可用,LLM 智能润色. Open-source speech-to-text with LLM post-processing, works offline.
Extremely fast and accurate audio transcriber surpassing Whisper. Fast on GPU or CPU.
Meeting transcription pipeline with speaker diarization and AI note-taking. GPU-accelerated ASR (NVIDIA Parakeet) + speaker attribution (Sortformer) + structured meeting notes via A2A protocol agents.
Add a description, image, and links to the parakeet-model topic page so that developers can more easily learn about it.
To associate your repository with the parakeet-model topic, visit your repo's landing page and select "manage topics."