Repolode
Submit
iflytek

iflytek/iFly-Skills

Official collection of iFLYTEK-built agent skills covering speech, OCR, translation, proofreading, and multimodal understanding.

View on GitHub
Stars
212
Forks
23
Open issues
36
Last commit
8 hours ago

What is it?

iFly-Skills is a repository of reusable skill packages built on iFLYTEK's AI capabilities. Each skill lives in its own directory with instructions, scripts, and metadata, so an agent or developer can install and call a specific capability such as text-to-speech, speech transcription, invoice OCR, or machine translation.

The current skills cover atomic abilities: Hyper TTS, voice cloning TTS, speed transcription, PDF and image OCR, invoice OCR, text proofreading, machine translation, image understanding, and video translation. It also includes a contract intelligence review skill and an animated sketch diagram skill that exports seamless-loop GIFs. Skills are distributed through several registries, and an npm package provides community nodes for self-hosted n8n.

The project is in beta, so skills, APIs, and configuration formats may change. Each skill's SKILL.md documents the required environment variables, such as the iFLYTEK app ID, API key, and API secret.

Key features

  • 01Provides text-to-speech, voice cloning, and high-speed audio transcription skills.
  • 02Includes OCR skills for general documents and structured invoice data.
  • 03Offers machine translation, video translation, and text proofreading skills.
  • 04Adds image understanding and contract intelligence review capabilities.
  • 05Ships an npm package with community nodes for self-hosted n8n.

Use cases

  • Adding speech or OCR capabilities to an AI agent workflow.
  • Automating invoice data extraction in a self-hosted n8n pipeline.
  • Building multilingual video localization or subtitle translation flows.
  • Running automated contract review with OCR and risk detection.

Quick start

  1. 1

    Install the n8n community node package via n8n Settings → Community Nodes

  2. 2

    Prepare the Python environment using the package installation guide

  3. 3

    Navigate to a skill directory and read its SKILL.md for setup details

    cd skills/iflytek-hyper-tts

Things to know

  • The project is in beta, so skills, APIs and configuration formats may change without notice.
  • Using the skills requires iFLYTEK API credentials (App ID, API key and secret) with quota for each service.
  • The n8n package requires Node.js 24.x and Python 3.10 or newer, and n8n Cloud is not supported.

Topics

#agent#skills#speech-recognition#ocr#machine-translation#text-to-speech#n8n#iflytek-astron#skill#skill-md

FAQ

What is iFly-Skills?
Official collection of iFLYTEK-built agent skills covering speech, OCR, translation, proofreading, and multimodal understanding. iFly-Skills is a repository of reusable skill packages built on iFLYTEK's AI capabilities. Each skill lives in its own directory with instructions, scripts, and metadata, so an agent or developer can install and call a specific capability such as text-to-speech, speech transcription, invoice OCR, or machine translation.
Is iFly-Skills free to use? What license does it have?
iFly-Skills is open source under the Apache-2.0 license. Check the license terms before using it in commercial products.
Is iFly-Skills still maintained?
Actively maintained. The last commit to iFly-Skills was on Oct 22, 2026.
What can I use iFly-Skills for?
Adding speech or OCR capabilities to an AI agent workflow. Automating invoice data extraction in a self-hosted n8n pipeline. Building multilingual video localization or subtitle translation flows. Running automated contract review with OCR and risk detection.
How do I install iFly-Skills?
Install the n8n community node package via n8n Settings → Community Nodes Prepare the Python environment using the package installation guide Navigate to a skill directory and read its SKILL.md for setup details: cd skills/iflytek-hyper-tts
Where can I get iFly-Skills?
The source code and installation instructions are on GitHub: https://github.com/iflytek/iFly-Skills

Summary generated by AI from the project's README. GitHub stats refresh daily.

Related projects