iflytek-speed-transcription

iflytek-speed-transcription is a skill for Claude Code, Codex from iflytek/iFly-Skills. It costs 90 tokens per session (1,884 once invoked), scanned A, original, Apache-2.0.

A speech-to-text tool that converts WAV, PCM, or MP3 audio into written text using iFlytek's transcription service. It supports Chinese, English, more than 202 Chinese dialects, automatic language detection, and speaker separation.

In plain words
What is it for?
Transcribe audio files, save the result to a text file, choose a language or accent, apply medical-domain optimization, and separate speakers in meetings.
Why use it?
It saves time when turning recordings into readable text and can distinguish speakers in supported recordings. It also supports domain-specific processing such as medical audio.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for openclaw. Also seen: built for openclaw.

Good fit Transcribe audio files, save the result to a text file, choose a language or accent, apply medical-domain optimization, and separate speakers in meetings.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/iflytek/ifly-skills/iflytek-speed-transcription
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add iflytek/iFly-Skills --skill iflytek-speed-transcription
Clone the repo
git clone --depth 1 https://github.com/iflytek/iFly-Skills

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for iflytek-speed-transcription

README.md
[![agentmods](https://agentmods.dev/badge/skills/iflytek/ifly-skills/iflytek-speed-transcription/github.svg)](https://agentmods.dev/skills/iflytek/ifly-skills/iflytek-speed-transcription)
Your own site
<a href="https://agentmods.dev/skills/iflytek/ifly-skills/iflytek-speed-transcription"><img src="https://agentmods.dev/badge/skills/iflytek/ifly-skills/iflytek-speed-transcription/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for iflytek-speed-transcription

Your own site · 80×15
<a href="https://agentmods.dev/skills/iflytek/ifly-skills/iflytek-speed-transcription"><img src="https://agentmods.dev/badge/skills/iflytek/ifly-skills/iflytek-speed-transcription.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 90 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,884 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00090 $0.01884
Opus 5 $0.00045 $0.00942
Sonnet 5 $0.00018 $0.00377
Haiku 4.5 $0.00009 $0.00188

Measured 12d ago against content hash 87cd2047c431, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

iflytek-speed-transcription scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/transcribe.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/iflytek-speed-transcription/SKILL.md · 173 lines

How it starts

The opening of the file, as written. The whole thing — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.

iFly Speed Transcription

Ultra-fast speech transcription service that converts audio files to text in record time - 1 hour of audio transcribes in ~20 seconds.

Quick Start

# Basic transcription (auto-detect language and dialect)
python3 scripts/transcribe.py /path/to/audio.mp3

# Save to file
python3 scripts/transcribe.py /path/to/audio.wav --output result.txt

# With domain-specific optimization
python3 scripts/transcribe.py /path/to/audio.mp3 --pd medical

# With speaker separation
python3 scripts/transcribe.py /path/to/meeting.mp3 --vspp-on 1 --speaker-num 2

Setup

1. API Credentials

Get credentials from iFlytek Open Platform:

  • APP_ID: Application ID
  • API_KEY: API key for authentication
  • API_SECRET: API secret for signing requests

2. Environment Variables

export XFEI_APP_ID="your_app_id"
export XFEI_API_KEY="your_api_key"
export XFEI_API_SECRET="your_api_secret"

API Parameters

Required Parameters

Parameter Description
file_path Path to audio file (MP3, 16kHz, 16-bit, mono)
--language Language code (default: zh_cn for Chinese+English+202 dialects)
--accent Accent (default: mandarin)

Optional Parameters

Parameter Type Description
--pd string Domain: court, finance, medical, tech, sport, edu, gov, game, ecom, car
--vspp-on int Speaker separation: 0=off, 1=on
--speaker-num int Number of speakers (0=auto, range 1-10)
--output-type int Output: 0=1best, 1=cnlbest, 2=multi-candidate
--postproc-on int Post-processing: 0=off, 1=on (default)
--enable-subtitle int Subtitle mode: 0=document, 1=subtitle
--smoothproc bool Smoothing: true=on, false=off (default: true)
--colloqproc bool Colloquial processing: true=on, false=off
--language-type int Language mode: 1=auto, 2=Chinese, 3=English, 4=Chinese-only
--dhw string Hot words (comma-separated, UTF-8)

Read the full file on GitHub · 173 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 12d ago First seen · 173 lines · 90 tokens per session scan A 87cd2047c431

Subscribe to this mod's changes

iflytek-speed-transcription is a skill published in the GitHub repository iflytek/iFly-Skills (218 stars, last pushed 2d ago), licensed Apache-2.0. It adds 90 tokens to every session and 1,884 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

scammer

A scam-message checker that analyzes suspicious texts, images, or conversation descriptions. It can identify the likely stage of a scam and suggest what the sender may try next.

naxiaoduo/Scammer.skill · 50 tokens

skill-creator

A guide for creating or improving an agent skill: a SKILL.md file that gives an AI a repeatable workflow for a specific task. It covers the skill’s name, search keywords, instructions, failure handling, and examples where needed.

zhinjs/zhin · 61 tokens

rolecraft

Install AI agent skills as roles & behaviors from any source — local folder, GitHub, GitLab, SSH git URL. Zero-dependency CLI with 87 agent targets (27 verified).

rolecraft-sh/rolecraft · 41 tokens

roadtrip-navigator

Generate North American road-trip itineraries as a map-first, offline-friendly single-file HTML page. Plans around daily driving segments, overnight stops, fuel/EV-charging, national-park reservations (Recreation.gov / NPS), seasonal road closures, and timezone/border crossings — for executable, decision-ready trips.…

Waybox-AI/roadtrip-skill · 106 tokens

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling.

Wholiver/Math.Skill · 33 tokens

webman

Expert skill for the webman framework (a long-lived, in-memory PHP framework based on workerman). Covers routing, controllers, middleware, database/Redis, custom processes, timers, coroutines (v2), plugin development, and guarding against memory leaks and cross-request state pollution under the resident process model.…

zjkal/webman-skill · 111 tokens