HackWare.ru
Tag

audio / voice / sound

AI / neural networks

Local speech recognition in 30 languages: a guide to using Qwen3-ASR-1.7B

Author: Aleksei Miloserdov ASR (Automatic Speech Recognition) audio / voice / sound audio transcription automatic transcription neural networks / artificial intelligence / AI Qwen3-ASR-1.7B Qwen3-ForcedAligner-0.6B Silero VAD speech recognition STT / speech-to-text Voice Activity Detection (VAD) AI / neural networks

Table of contents 1. Free and unlimited automatic speech recognition on your own computer (local ASR and STT) 2. A free model for multilingual speech recognition on your own computer 3. How to install Qwen3-ASR-1.7B 3.1 How to ins…

Read article →
AI / neural networks

AI-powered desktop app for converting texts of any length into speech

Author: Aleksei Miloserdov audio / voice / sound ComfyUI Fun-ASR-MLT-Nano-251 generative AI GUI MiAl AI Text-to-Speech neural networks / artificial intelligence / AI Qwen3-ASR-1.7B SenseVoiceSmall Silero VAD TTS (Text-to-Speech) Voice Activity Detection (VAD) VoxCPM2 AI / neural networks

Table of contents 1. Text-to-speech program for generating speech from texts in any language using a neural network 2. Installing Hy-MT2 with a graphical interface 3. How to use VoxCPM2 with a graphical interface for text-to-speec…

Read article →
AI / neural networks

Local TTS in 30 languages with voice cloning (VoxCPM2 usage guide)

Author: Aleksei Miloserdov audio / voice / sound ComfyUI generative AI neural networks / artificial intelligence / AI TTS (Text-to-Speech) VoxCPM2 AI / neural networks

Table of contents 1. Generating speech from text in different languages on your own computer 2. Free text-to-speech program supporting English, Chinese, Spanish, French, German, and other languages 3. How to install VoxCPM2 3.1 Wh…

Read article →
↑