Search Results for "multi"

Epicenter is a free, open-source framework and application ecosystem designed for building local-first software with user-controlled data storage. It uses conflict-free replicated data types through Yjs to synchronize information between devices without relying on a central database. Each application stores its data locally, allowing users to continue working without an internet connection. Its architecture supports structured tables, key-value storage, and rich text within unified data...

https://github.com/GyratingSeaCow/tangent - Go here for docker install instruc. A notes app for the people, forever, for free on your own hardware synced up! Tangent is a self-hosted voice brain-dump app. You hit record, dump whatever's in your head, and a Dockerized home server running Whisper on your own GPU transcribes it automatically. Your audio, transcripts, and notes never leave hardware you own — no cloud, no third party, no subscription. Features: Three capture modes —...

Java application for chatting to generative AI Llama3. * The user can speak into the microphone (speechToText), edit the recognized text and send it to the AI. * The AI ​​responds and the server returns that response in real time, and the sentences converted to audio (textToSpeech), and the application broadcasts them through the speaker. The application is prepared so that only one user occupies the server's resources, so if the server is busy, in theory it will not let you...

Coqui STT is a fast, open-source, multi-platform, deep-learning toolkit for training and deploying speech-to-text models. Coqui STT is battle-tested in both production and research. Multiple possible transcripts, each with an associated confidence score. Experience the immediacy of script-to-performance. With Coqui text-to-speech, production times go from months to minutes.

...Its capabilities include verbatim and formatted transcription, speaker attribution, word-level timestamps, language identification, code-switching, and audio question answering. Configurable reasoning modes enable advanced audio analysis, while native Multi-Token Prediction supports speculative decoding. Available in BF16, FP8, and NVFP4 precision, it integrates with NVIDIA NeMo Speech, vLLM, SGLang-Omni, and Hugging Face Transformers for speech processing applications.