Tag
Explore by tags
Reimplements OpenAI's Whisper speech-to-text on the CTranslate2 inference engine, running up to 4x faster at the same accuracy while using less memory. Adds a batched pipeline, 8-bit quantization, VAD filtering, and word-level timestamps.
Provides an uncensored, self‑hostable studio for generating AI images, videos, and lip‑synced talking videos in browser or desktop. Integrates 200+ models via Muapi.ai, supports local inference (stable-diffusion.cpp), multi-image inputs and workflow automation — no content filters.
Upload your own documents, PDFs, slides, or web pages and ask questions answered only from that material, with inline citations pointing to the exact passage used. Audio Overview turns your sources into a downloadable two-host podcast discussion.
Converts microphone or streamed audio to text with sub-second latency, pairing WebRTC/Silero voice-activity detection and wake-word activation with swappable local backends — faster-whisper by default, plus whisper.cpp, Moonshine, and sherpa-onnx.
Converts videos between languages by transcribing audio, translating subtitles, and producing AI dubbing—supports local and online ASR/LLM/TTS providers, speaker diarization, voice cloning, and GUI/CLI workflows for batch or headless use.
Generates expressive multilingual speech from text, with sub-word control over prosody and emotion via inline tags like [whisper] or [angry]. Handles multi-speaker, multi-turn dialogue; the weights ship under a research-only license.
Terminal CLI for on-device Whisper ASR using Hugging Face Transformers + Optimum, with optional Flash Attention 2, batching, and diarization support — focused on high-throughput transcription on NVIDIA GPUs and Apple Silicon (mps).
Unifies text-to-speech, singing voice synthesis, voice conversion, and text-to-audio/music in one PyTorch framework with shared vocoders and a common evaluation pipeline. Ships recipes, pretrained checkpoints, and visualizations of classic models.
Performs speaker diarization (who spoke when) with pyannote-audio: combines voice-activity detection, speaker-change and overlapped-speech detection to produce time-stamped speaker segments; compatible with Hugging Face Endpoints and ASR pipelines.
Hands-free voice-first companion with a Live2D avatar for real-time conversations with LLMs. Cross-platform web and desktop clients, runs locally or via cloud APIs, supports local ASR/TTS and modular customization for personas and models.
Collection of runnable model implementations — LLaMA, Mistral, Stable Diffusion, Whisper, CLIP, plus LoRA fine-tuning — ported to the MLX array framework so they run natively on Apple silicon's unified memory rather than CUDA.
Builds realtime voice AI agents that run as server-side participants in WebRTC rooms — mix STT, LLM, and TTS providers or use one realtime model. Adds semantic turn detection, SIP telephony, multi-agent handoffs, and an LLM-judge test harness.