qwen3-tts-mlxLocal Qwen3-TTS speech synthesis on Apple Silicon via MLX. Use for offline narration, audiobooks, video voiceovers, and multilingual TTS.
Install via ClawdBot CLI:
clawdbot install h1bomb/qwen3-tts-mlxGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Generated Mar 22, 2026
Authors and publishers can generate audiobook narration directly on Mac without cloud services, ensuring privacy and reducing costs. Supports multilingual content with built-in voices like Serena for storytelling or Uncle_Fu for authoritative tones, ideal for self-publishing or educational materials.
Content creators and marketers produce voiceovers for videos, ads, or tutorials in 11 languages with style control (e.g., news anchor tone). Enables rapid localization without hiring voice actors, perfect for YouTube channels, corporate training, or social media campaigns.
Developers clone user voices from short audio samples to create custom AI assistants or chatbots with familiar tones. Useful for accessibility tools, personalized customer service, or entertainment apps where voice identity enhances user engagement.
Game studios and animators design unique character voices from text descriptions (e.g., 'elderly wise male') using VoiceDesign mode. Allows iterative prototyping without recording sessions, speeding up production for indie games or animated shorts.
Podcasters generate intros, outros, or full episodes with controlled emotions (e.g., excited, calm) using built-in voices like Ryan or Aiden. Ideal for remote creators needing reliable, high-quality speech synthesis without internet dependency.
Offer a cloud-based platform with advanced features like batch processing or API access, built on this local tool for core TTS. Charge monthly fees for businesses needing scalable, multilingual voiceovers without hardware limits.
Sell a packaged desktop application with GUI, leveraging the skill's CLI and Python API for easy use. Target indie creators, educators, or small studios who prefer offline tools with lifetime access and updates.
Provide custom integration services for companies embedding TTS into products (e.g., e-learning platforms, assistive devices). Offer support, training, and tailored voice models based on client needs, using the skill's modular modes.
💬 Integration Tip
Ensure ffmpeg is installed via Homebrew for audio processing, and use the Python API's generate_audio function for streamlined integration into existing workflows.
Scored Apr 19, 2026
AI cinematic video production powered by CellCog. Short films, music videos, brand films, widescreen cinematics. Consistent characters, cinematic lighting, visual storytelling — grand compositions from a single prompt.
Download online videos with quality and format controls using yt-dlp for reliable local saves.
Google Trends关键词搜索热度对比与趋势分析,支持全球区域和自定义时间范围。当用户提到谷歌趋势、关键词随时间变化的热度、搜索兴趣对比、关键词趋势分析、季节性趋势检测、区域搜索热度、关键词热力图、多个关键词在Google上的对比、Google Trends, keyword popularity comp...
Render music videos from audio files and lyrics using Remotion. Accepts audio + LRC/JSON lyrics + title to produce MP4 videos with waveform visualization and synced lyrics display. Use when users mention MV generation, music video rendering, creating video from audio/lyrics, or visualizing songs.
Control Spotify playback on remote Spotify Connect devices (speakers, TVs, Echo, phone, desktop). Use when user wants to play music, pause, skip, adjust volume, list audio devices, or transfer playback to a specific device. Supports multiple Spotify accounts with named profiles. Requires Spotify Premium.
微云网盘 MCP 接口完整技能。包含目录列表查询(weiyun.list)、按分类拉取文件列表(weiyun.list_by_category)、批量下载(weiyun.download)、批量删除(weiyun.delete)、文件上传(weiyun.upload)、生成分享外链(weiyun.gen_shar...