Content
Plugin
noizai-skills
Central repository for managing Skills to "human" vibe-talking.
Plugin Signal57/100Fair
maintained55
capable46
documented75
adopted58
Install
$ npx -y skills add noizai/skills --agent claude-code
Run the curl in your terminal, the rest in Claude Code.
What's inside
Skills
8/characteristic-voiceUse this skill whenever the user wants speech to sound more human, companion-like, or emotionally expressive. Triggers include: any mention of 'say like', 'talk like', 'speak like', 'companion voice', 'comfort me', 'cheer me up', 'sound more human', 'good night voice', 'good/chat-with-anyoneChat with any real person or fictional character in their own voice by automatically finding their speech online, extracting a clean reference sample, and generating audio replies. Also supports generating a matching voice from an uploaded image. Use when the user says/daily-news-casterFetches the latest news using news-aggregator-skill, formats it into a podcast script in Markdown format, and uses the tts skill to generate a podcast audio file. Use when the user asks to get the latest news and read it out as a podcast./sound-fxUse this skill whenever the user wants to generate sound effects, ambient audio, or short audio clips from a text description. Triggers include: any mention of 'sound effect', 'sfx', 'generate sound', 'make a sound', 'audio effect', 'ambient sound', 'foley', 'sound clip',/speech-to-textUse this skill whenever the user wants to transcribe audio to text, convert speech to text, or get a transcript from an audio or video file. Triggers include: any mention of 'transcribe', 'transcription', 'speech to text', 'STT', 'convert audio to text', 'what does this audio/template-skillReusable template for authoring new Agent Skills with clear triggers, workflow, and I/O contracts.
Show all 8 skillsShow fewer
/ttsUse this skill whenever the user wants to convert text into speech, generate audio from text, or produce voiceovers. Triggers include: any mention of 'TTS', 'text to speech', 'speak', 'say', 'voice', 'read aloud', 'audio narration', 'voiceover', 'dubbing', or requests to turn/video-translationTranslate and dub videos from one language to another, replacing the original audio with TTS while keeping the video intact.
Badges
1README
1Unmute your intelligent bot
English | ็ฎไฝไธญๆ
Central repository for managing Skills to "human" vibe-talking.
Install with npx skills add
# List skills from GitHub repository
npx skills add NoizAI/skills --list --full-depth
# Install a specific skill from GitHub repository
npx skills add NoizAI/skills --full-depth --skill tts -y
# Install from GitHub repository
npx skills add NoizAI/skills
# Local development (run in this repo directory)
npx skills add . --list --full-depth
Highlights
- ๐ Secure and local-first: run skills on your own machine to keep sensitive text and assets localized.
- ๐ง Character-style controls: tune fillers, emotion, and speaking presets for companion-like output.
- ๐๏ธ Production-ready voice: from quick TTS generation to timeline-aligned rendering.
- ๐ค One-command delivery to chat platforms: generate speech and send it as a native voice message to Feishu, Telegram, or Discord โ zero extra code.
Available skills
| Name | Description | Documentation | Run command |
|---|---|---|---|
| tts | Convert text into speech with Kokoro or Noiz: simple mode, timeline-aligned rendering, precise duration control, and reference-audio voice cloning. | SKILL.md | npx skills add NoizAI/skills --full-depth --skill tts -y |
| chat-with-anyone | Chat with any real person or fictional character in their own voice by automatically finding their speech online, extracting a clean reference sample, and generating audio replies. | SKILL.md | npx skills add NoizAI/skills --full-depth --skill chat-with-anyone -y |
| characteristic-voice | Make generated speech feel companion-like with fillers, emotional tuning, and preset speaking styles. | SKILL.md | npx skills add NoizAI/skills --full-depth --skill characteristic-voice -y |
| video-translation | Translate and dub videos from one language to another, replacing the original audio with TTS while keeping the video intact. | SKILL.md | npx skills add NoizAI/skills --full-depth --skill video-translation -y |
| daily-news-caster | Fetch the latest real-time news and automatically generate a dual-host conversational podcast with audio. | SKILL.md | npx skills add NoizAI/skills --full-depth --skill daily-news-caster -y |
| sound-fx | Generate any sound effect from a text description โ animals, ambience, cartoon sounds, sci-fi, and more. One command, 1โ30 seconds, WAV/MP3/FLAC output. | SKILL.md | npx skills add NoizAI/skills --full-depth --skill sound-fx -y |
Quick Verify
For example, characteristic-voice
bash skills/characteristic-voice/scripts/speak.sh \
--preset comfort -t "Hmm... I'm right here." -o comfort.wav
English Audio Demos
Sample outputs for quick listening (MP4 for inline playback):
- Breaking news style
https://github.com/user-attachments/assets/e1e75371-49e2-4858-9993-428d999c3723
- Mindful calm style
https://github.com/user-attachments/assets/d2e6472d-9edf-449d-a5ee-51ad7e19a861
- Podcast intro style
https://github.com/user-attachments/assets/e8f78ffa-7f12-4475-b1af-09161b3ee01b
- Startup hype style
https://github.com/user-attachments/assets/0d3b8af9-2288-4a63-9246-2748ed232b0e
Noiz API Key (recommended)
For the best experience (faster, emotion control, voice cloning), get your API key from developers.noiz.ai/api-keys:
bash skills/tts/scripts/tts.sh config --set-api-key YOUR_KEY
The key is persisted to ~/.noiz_api_key and loaded automatically. Alternatively, pass --backend kokoro to use the local Kokoro backend.
Contributing
For skill authoring rules, directory conventions, and PR guidance, see CONTRIBUTING.md.
Feedback & Discussion
Project Trends
GitHub Star Trend
Git Clone Trend
File tree
34noizai/skillsView on GitHub
.github/
workflows/
tts-tests.yml
.gitignore
Clones.png
CONTRIBUTING.md
examples/
audio/
demo-breaking-news.mp4
demo-mindful-calm.mp4
demo-podcast-intro.mp4
demo-startup-hype.mp4
README.md
README.zh-CN.md
skills/
characteristic-voice/
scripts/
speak.sh
SKILL.md
chat-with-anyone/
scripts/
extract_ref_segment.py
voice_design.py
SKILL.md
daily-news-caster/
SKILL.md
README.md
sound-fx/
ref_3rd_party.md
scripts/
sfx.py
SKILL.md
speech-to-text/
scripts/
stt.py
SKILL.md
template-skill/
SKILL.md
SKILL.zh-CN.md
tts/
ref_3rd_party.md
scripts/
noiz_tts.py
render_timeline.py
test_tts.py
text_to_srt.py
tts.py
SKILL.md
video-translation/
scripts/
replace_audio.sh
srt_to_duck.py
SKILL.mdFAQ
noizai-skills is a Claude Code plugin with 8 hand-picked skills for content work, indexed on Flowy. Install it with the command on its page. It includes characteristic-voice, chat-with-anyone, daily-news-caster. Its skills do not fire on their own yet. Request auto-invocation to have Flowy route them as you prompt. Free and open source.
- What is noizai-skills?
- Central repository for managing Skills to "human" vibe-talking.
- How do I install noizai-skills?
- Run these in Claude Code: npx -y skills add noizai/skills --agent claude-code. Then prompt normally.
- Does noizai-skills auto-invoke its skills?
- Not yet. It is indexed on Flowy as a plain plugin. Request auto-invocation on its page and Flowy will route its skills for you as you prompt.
- Is noizai-skills free?
- Yes. Flowy is free and open source, with nothing gated. You can read every skill in full before you install.