跳到正文
TakoAPI
返回技能列表

assemblyai-transcribe

由 tristanmanchester 提供

Speech & Transcription
2.6k下载量由 clawskills.sh 提供
3星标
0浏览量
0 个赞登录后即可为这个技能点赞
—暂无评分
你的评分

简介

Transcribe audio/video with AssemblyAI.

描述

该技能的功能

Transcribes audio and video using AssemblyAI, with support for speaker diarisation, named speaker mapping, language detection, and translation. Outputs include Markdown, structured JSON, subtitles, and bundle manifests designed for AI agent consumption. Post-processing options include AssemblyAI Speech Understanding and LLM Gateway for extraction and summarization.

Combines transcription, diarisation, speaker identification, translation, and LLM-based extraction in a single CLI built for scripted agent workflows rather than interactive use.

何时使用

  • Transcribing recorded meetings with labeled speaker turns
  • Generating subtitles for multilingual video content
  • Extracting structured summaries from podcast episodes
  • Identifying speakers by name or role in interview recordings
  • Converting audio into agent-readable Markdown transcripts

示例工作流

输入

User asks: Transcribe this meeting recording and label each speaker

智能体
  1. 1

    Runs the transcribe command with --speaker-labels and --bundle-dir flags on the audio file

  2. 2

    CLI uploads the file to AssemblyAI and polls until transcription completes

  3. 3

    Reads the manifest from the bundle directory to locate output files

  4. 4

    Returns the Markdown transcript with speaker-labeled turns to the user

输出

Markdown transcript with labeled speaker turns, plus agent JSON and manifest saved to the bundle directory

前置要求

  • ASSEMBLYAI_API_KEY environment variable
  • AssemblyAI account (assemblyai.com)

安装

clawhub install tristanmanchester/assemblyai-transcribe

运行 CLI 命令,或把这段提示词粘贴到 Claude Code、Cursor、Codex 或你在用的任意编程智能体里。

链接