One-step Turkish text-to-speech trained with a drifting objective (Kyutai learned-temperature recipe)

Training Higgs Audio TTS v3

Phonon: open speech recognition models (Phonon-2, Phonon-1) — CLI, CPU and CUDA images

Non-autoregressive System 1 decision engine. Typed choice, score and yes/no decisions over any text in a single forward pass, in 100+ languages, with a router that picks the right checkpoint per re…

A visual catalog of text-to-speech architectures, with model diagrams, concise descriptions, and primary sources.

Replace port numbers with stable, named local URLs. For humans and agents.

TypeScript SDK for ZIMRA FDMS fiscalisation — direct device registration, mTLS, receipt signing, fiscal days, offline queue, QR codes

Open-weights speaker diarization for pyannote.audio 4.x: WavLM-Base+ / Conformer segmentation + SimAM-ResNet34 embeddings, by Reway.

Beautiful pdf components, built on Takumi and Forme. 100% Free, Zero config, one command setup.

Complete guide and toolkit for fine-tuning Moonshine ASR models for custom languages. Includes French example with 21.8% WER.

Open-source observability platform for logs, traces, metrics, alerts, and incidents

Speech synthesis (TTS) in low-resource languages by training from scratch with Fastpitch and fine-tuning with HifiGan

FireRedTTS3: Multilingual and Multi-Dialect Voice Cloning with Instruction-Guided Voice Design and Speech Editing

The open-source communication infrastructure for agents and products

Create beautiful moving gradients on Framer, Figma and React

Medplum is a healthcare platform that helps you quickly develop high-quality compliant applications.

A one-of-a-kind resume builder that keeps your privacy in mind. Completely secure, customizable, portable, open-source and free forever. Try it out today!

VoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning

Provide with pre-build flash-attention 2 and 3 package wheels on Linux and Windows using GitHub Actions

VyvoTTS: LLM-Based Text-to-Speech Training Framework

Convert Word, PowerPoint, Excel, OpenDocument, RTF, EPUB, CSV, and PDF to clean Markdown. Built in Rust, with Node.js and Python bindings.

BandIt: Cinematic Audio Source Separation

Extract any sound with text prompts. Memory-optimized SAM-Audio with modern UI.

WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)

Convert PDF to markdown + JSON quickly with high accuracy