Generate speech with voice cloning and transcribe audio to TXT, SRT, or ASS formats.
npx skills add https://github.com/skills-router/skills-store --skill qwen-audio
Please help me install this Agent Skill. Skill: qwen-audio Source: https://github.com/skills-router/skills-store/tree/main/skills/qwen-audio Command: npx skills add https://github.com/skills-router/skills-store --skill qwen-audio
This Skill addresses the need for high-quality, efficient audio processing, enabling users to generate speech from text and transcribe spoken audio with advanced AI models.
Use the qwen-audio skill to convert the text 'Hello, world!' into an audio file named 'output.wav'.
High-intent search queries and answers about installing and using this skill.
Speech-to-text transcription converts audio files into text with support for multiple output formats including TXT, SRT, and ASS. Using Qwen models, it processes spoken audio to generate formatted text transcripts for subtitle creation.
Text-to-speech with voice cloning generates natural-sounding speech from text using Qwen models. It supports custom voice creation, allowing you to produce AI voiceovers for audio files like WAV without recording original audio.
Yes, Qwen audio processing requires Python 3.10 or higher and platform-specific ML libraries. Dependencies include mlx-audio, torch, soundfile, and numpy to execute the underlying text-to-speech and speech-to-text models.
The best way to create subtitles from audio recordings is using speech-to-text transcription with Qwen models. It automatically transcribes spoken audio into text and outputs subtitle formats like SRT and ASS for direct video integration.
Yes, mlx-audio supports generating audio files from text input. Combined with Qwen text-to-speech capabilities, it processes text strings to synthesize speech and outputs the resulting audio into standard file formats like WAV.
psd401Generate speech audio with MLX acceleration and the Kokoro-82M model on Apple Silicon.
dawsonblockTranscribe video speech into SRT/ASS subtitles and burn them into video.
astoreyaiTranscribe audio from files or microphones using multiple speech-to-text engines.
kaivyyTranscribe audio files with OpenAI Whisper and synthesize speech from text.
