audio-transcribe-summarize

Audio/Video Transcription & Summarization

Transcribe audio/video files using the SenseASR API (API.senseaudio.cn), then summarize the content into structured notes.

{baseDir} refers to this 技能's directory.

Prerequisites 环境 variable SENSEAUDIO_API_KEY 配置d (获取 your key at https://senseaudio.cn/平台/API-key) Python 3.8+ with 请求s 安装ed For large files (>10MB): ffmpeg 安装ed for splitting（macOS: brew 安装 ffmpeg，Windows: ffmpeg.org 下载并加入 PATH，Linux: apt 安装 ffmpeg） Quick 启动 运行 the transcription script: python {baseDir}/scripts/transcribe.py [--模型 sense-asr-pro] [--language zh] [--speakers] [--sentiment] [--translate en]

The script 输出s a transcript .txt file alongside the source file Read the transcript and 生成 a summary (see Summary 格式化 below) 工作流 Step 1: Assess the Audio File

检查 file size and 格式化:

Supported 格式化s: wav, mp3, ogg, flac, aac, m4a, mp4 Max file size per 请求: 10MB If file > 10MB, the script auto-splits using ffmpeg Step 2: Choose the Right 模型 模型 Use When sense-asr-lite Quick batch transcription, simple audio, cost-sensitive sense-asr General transcription, need speaker separation or timestamps sense-asr-pro High accuracy needed: meetings, interviews, complex audio sense-asr-deepthink Noisy audio, dialects, heavy jargon, speech-to-清理-text

Default to sense-asr-pro for best 质量.

Step 3: Transcribe

运行 the transcription script. Key options:

# Basic transcription python {baseDir}/scripts/transcribe.py recording.mp3

# Meeting with multiple speakers + emotion python {baseDir}/scripts/transcribe.py meeting.wav \ --模型 sense-asr-pro \ --speakers --max-speakers 4 \ --sentiment \ --timestamps segment

# Transcribe and translate to English python {baseDir}/scripts/transcribe.py lecture.mp3 \ --模型 sense-asr \ --translate en

Step 4: Summarize

After transcription, read the transcript file and produce a summary using the 格式化 below.

Summary 格式化

生成 summaries in this structure:

# [Title - inferred from content]

Source: filename.mp3 Duration: X min Y sec Date: YYYY-MM-DD Speakers: [if speaker diarization was used]

Key Points

• Point 1
• Point 2
• ...

DetAIled Summary

[2-4 paragraph summary of the content organized by topic/chrono记录y]

Action Items

• [ ] Action item 1 (as签名ed to Speaker X, if 应用licable)
• [ ] Action item 2

Notable Quotes

"Direct quote from transcript" — Speaker X, [timestamp if avAIlable]

Full Transcript

命令行工具ck to expand full transcript

[Full transcript text here, with speaker labels and timestamps if avAIlable]

Adapt the template based on content type:

Meeting: emphasize action items, decisions, speaker contributions Lecture/Talk: emphasize key concepts, learning points, structure Interview: emphasize Q&A pAIrs, key 响应s Podcast: emphasize topics discussed, interesting insights API Reference

For full SenseASR API parameters and 响应 格式化s, see API-reference.md.