OCR software, free and offline
Faster Whisper transcription with CTranslate2
Generate audiobooks from EPUBs, PDFs and text with captions
A GUI tool for extracting hard-coded subtitle (hardsub) from videos
A TTS that fits in your CPU (and pocket)
Use Microsoft Edge's online text-to-speech service from Python
Robust Speech Recognition via Large-Scale Weak Supervision
Comprehensive Gradio WebUI for audio processing
Contexts Optical Compression
Open source healthcare AI
Unlimited, private and free Speech-To-Text program
Stable Diffusion web UI
1 min voice data can also be used to train a good TTS model
EPUB to audiobook converter, optimized for Audiobookshelf
Automated translation solution for visual novels
Visual Causal Flow
Free, high-quality text-to-speech API endpoint to replace OpenAI
A modular voice assistant application for experimenting
95% token savings. 155x faster queries. 16 languages
OCR model for complex documents with layout-aware structured outputs
Google Gen AI Python SDK provides an interface for developers
Python library and CLI tool to interface with Google Translate
AsrTools: Smart Voice-to-Text Tool
Enhances Tesseract OCR output using LLMs (local or API)
Qwen3-ASR is an open-source series of ASR models