skills.rest
iflytek
iflytekOFFICIAL
Explore all skills by this author →
WebsiteGitHub

ifly-speed-transcription

Transcribe long audio files via the iFLYTEK Speed Transcription API.

217|27|Updated Mar 30, 2026
Search Tags:#transcription#developer-tools#language-detection#audio-processing#speed-transcription#ai-api
One-click install
npx skills add https://github.com/iflytek/iFly-Skills --skill ifly-speed-transcription
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ifly-speed-transcription
Source: https://github.com/iflytek/iFly-Skills/tree/main/ifly-speed-transcription
Command: npx skills add https://github.com/iflytek/iFly-Skills --skill ifly-speed-transcription

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires requests, urllib3, and includes scripts (resource) components.

What problem does it solve?

Ultra-fast transcription for long audio files using the iFLYTEK Speed Transcription API, drastically reducing processing time and manual effort.

Core Features & Use Cases

  • Ultra-fast transcription of long recordings (up to 5 hours) with auto language detection.
  • Supports multiple languages/dialects (Chinese, English, 202+ dialects) and optional domain optimization, speaker separation, and subtitle output.
  • Easy programmatic integration via a Python client script and CLI-friendly workflow for batch processing.

Quick Start

Provide the path to an audio file to start an end-to-end transcription task and retrieve the text result.

Frequently Asked Questions about ifly-speed-transcription

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I transcribe long audio recordings quickly using an AI API?▼

Transcribe long audio recordings quickly by uploading files to an AI API, creating a transcription task, and polling for results. This approach supports recordings up to 5 hours with automatic language detection.

What audio formats and languages are supported for speed transcription?▼

Speed transcription supports MP3, WAV, and PCM audio inputs. It handles Chinese, English, and 202+ dialects with automatic language detection, plus optional domain optimization and speaker separation.

Do I need environment variables to use the iFLYTEK Speed Transcription API?▼

Yes, iFLYTEK Speed Transcription API requires credentials stored in environment variables XFEI_APP_ID, XFEI_API_KEY, and XFEI_API_SECRET to authenticate and process audio transcription tasks.

Can I get subtitle output and speaker separation from audio transcription?▼

Audio transcription offers optional subtitle output and speaker separation. It processes long recordings with auto language detection, supporting multiple languages and dialects for up to 5 hours of audio.

What's the best way to batch process audio transcription for long files?▼

Batch process audio transcription by using a Python client script and CLI-friendly workflow. Upload files, create transcription tasks, and poll for results to handle long recordings efficiently.

Related Skills

Explore More Software Engineering Skills→
team-telnyxteam-telnyx
3

telnyx-stt

Transcribe MP3, WAV, OGG, M4A, and WebM audio files via the Telnyx Speech-to-Text API.

Official
Basic
ericwang915ericwang915
38

pdf_reader

Extract text and metadata from PDFs using PyPDF2.

Community
Intermediate
scholarclawscholarclaw
5

paper-search

Search academic papers via the scholar.club API with formatted or raw responses.

Official
Intermediate
tamireslaeao-progtamireslaeao-prog

openai-whisper

Transcribe local audio files to plain text using the Whisper CLI.

Community
Intermediate