Results for "whisper"

Nearly-live implementation of OpenAI's Whisper for real-time speech-to-text transcription. Supports faster-whisper, tensorrt, and openvino backends with WebSocket streaming. MIT licensed.

Canonical open speech-to-text model codebase with widespread ecosystem support and many downstream implementations.

Cross-platform local speech-to-text app that uses Whisper or Parakeet with voice-activity detection, then pastes the transcription into the active application. MIT licensed.

Multilingual AI speech recognition, text-to-speech, and zero-shot voice cloning WebUI. GPL-3.0 licensed.

macOS dictation application providing real-time audio transcription and drag-and-drop file transcription using Whisper and Parakeet models. MIT licensed.

MIT-licensed native macOS menu-bar dictation app whose free Local mode runs Whisper (WhisperKit) or NVIDIA Parakeet (FluidAudio) on device and pastes the text where you dictated it, with optional hosted Polishing and paid cloud transcription.

Fast inference engine for Transformer models supporting OpenNMT and Hugging Face models. Optimized for CPU and GPU with batching, quantization (INT8/FP16), and dynamic memory management. Powers faster-whisper and other production deployments. MIT licensed.

Local-first Expo and FastAPI Japanese practice app for Korean speakers that uses Whisper-compatible STT, local TTS, and embedding-based dialogue matching without a runtime LLM.

PyTorch speech toolkit with recipes for ASR, TTS, speaker recognition, and speech enhancement.

Local-first Windows desktop app that turns long videos and livestreams into vertical clips, using faster-whisper for word-level captions and a local LLM through Ollama to pick highlights. AGPL-3.0 licensed.

macOS dictation app that types transcribed speech at the cursor in any application, with whisper.cpp and the Whisper model bundled so it runs offline with no setup. Also records meetings on-device and generates summaries through a bundled llama.cpp. GPL-3.0 licensed.

Privacy-first local AI meeting assistant for real-time transcription and summary generation. MIT licensed.

Open-source app that brings small language models directly to your phone. Run AI 100% privately on iOS and Android with no cloud required. MIT licensed.

Local-first AI voice studio to clone voices, generate speech in multiple languages, and dictate text locally. MIT licensed.

Self-hosted app that turns long videos into vertical short clips using faster-whisper transcription, LLM clip selection, face-tracking 9:16 reframing, and animated captions. MIT licensed.

Self-hosted webUI for 30+ generative AI models. Generate multimedia content with AI on your own computer, even without dedicated GPU (8GB RAM minimum). Works offline once deployed. GPL-3.0 licensed.

Open speech and sound generation family focused on expressive, long-form text-to-speech with streaming and multi-speaker support.

The de facto standard library for pretrained NLP models. 1M+ models, 250,000+ downloads/day. BERT, GPT, Llama, Qwen, and hundreds more.

Scalable framework and model codebase for speech, language, and multimodal AI with recipes and deployment guidance.

Open Frontier Voice AI toolkit spanning speech understanding, generation, and multilingual TTS workflows, with active research and deployment tooling.

Complete speech toolkit with ASR, TTS, diarization, source separation, and VAD across embedded and edge environments via ONNX Runtime.

Open-source on-device voice AI toolkit for low-latency speech-to-text, intent recognition, and text-to-speech.

C/C++ speech-to-text inference library running 16+ model families on the ggml runtime with GPU acceleration.

TT-Metalium + TT-NN operator stack for building and optimizing kernels on Tenstorrent AI accelerators. Apache 2.0 licensed.