Edge Online Text-to-Speech
Paste the following prompt into your AI chat to install this skill:
Please install @user_c9d52b8e/edge-tts-mf according to https://skillhub.cn/install/skillhub.md.
About this skill
Problem to Solve
Local scripts or CI jobs often need to turn text into a playable MP3 quickly, without applying for a TTS API key or maintaining a paid voice service. Edge TTS uses Microsoft Edge online speech synthesis to provide a no-key, free text-to-speech path, useful for automated announcements, audio previews, and lightweight media generation.
How It Works
The skill exposes two core scripts:
- scripts/tts_edge.py: converts text to MP3 using edge-tts.
- scripts/tts_play.py: plays MP3 headlessly with pyglet.
Common parameters include --voice to select a voice, --rate to adjust speech rate, --pitch to adjust pitch, --volume to adjust volume, --output to set the output path, and --play to play the result after synthesis. The default Chinese voice is zh-CN-XiaoxiaoNeural; alternatives include zh-CN-YunxiNeural and zh-CN-YunyangNeural for different speaking styles. --list shows available voices, with the full list in references/voices.md.
Boundaries
It fits lightweight, free, Chinese-first TTS tasks where the main goal is producing an MP3 file or triggering playback in a local workflow. Because it relies on Edge’s online service, availability and output stability may depend on network access and upstream policy. It is not ideal for high-concurrency, SLA-sensitive, or strictly offline production use.
Use Cases
- Generate MP3 from text in automation with output path.
- Compare Chinese voices and adjust rate, pitch in tests.
- Play generated MP3 on headless servers via pyglet.
- List available Chinese voices and pick news or cute styles.
Best For
- Automation engineers turning script logs or text into MP3.
- Voice product engineers testing Chinese styles and adjusting rate or pitch.
- Backend engineers generating and triggering audio playback on headless servers.
- Integration engineers maintaining TTS config and looking up Chinese voices.
Related Skills
A ComfyUI image-generation skill that uses a five-step dialog to collect prompts, prefill templates, confirm parameters, submit API jobs, and return results.
A design-system guidance skill for Impeccable that produces token-based rules, component states, accessibility criteria, and QA checklists.
Director-level video lapian that diagnoses material precision, then produces frame evidence, director analysis, a style bible, and a showcase video.
Plan and brief Amazon MAIN, Listing, and A+ image sets from verified product facts, then return plan and image QA status.