Skip to main content
affpapa.org
RU EN
subagent

podcast-transcriber — Claude Code subagent: how to install and use

Subagent for turning podcast audio and video into structured JSON transcripts. It runs FFMPEG to process tracks, identifies speakers, and calculates exact timestamps.

Install into Claude Code · claude-code-templates All methods and platforms ↓ 
npx claude-code-templates@latest --agent ffmpeg-clip-team/podcast-transcriber
Open on GitHub

What podcast-transcriber does

This agent processes recordings directly through shell utilities. It starts by inspecting media streams with ffprobe to determine format details and runtime. Then it extracts the audio track into a single-channel 16 kHz WAV file via FFMPEG, applying a loudnorm filter whenever volume levels need leveling.

Longer audio runs are divided into chunks for easier handling. The agent assigns millisecond-level timestamps to each spoken phrase, distinguishes separate voices, and outputs everything as a JSON file. This payload includes confidence ratings alongside metadata like detected language and total run time.

Local ffmpeg and ffprobe binaries must be present in the path. Without them, shell execution fails immediately during the audio extraction stage.

What it helps with

  • extract audio from video files into 16 kHz mono WAV
  • normalize uneven loudness across podcast recordings
  • slice lengthy audio files into timed chunks
  • generate JSON transcripts with speaker labels and millisecond timings

Example prompts for the agent

  • Extract the audio from interview.mp4 and produce a JSON transcript with speaker tags.
  • Normalize episode_12.wav and transcribe speech with millisecond timestamps.

How to install podcast-transcriber

1claude-code-templates

npx claude-code-templates@latest --agent ffmpeg-clip-team/podcast-transcriber

2Manually: put the files in place

.claude/agents/podcast-transcriber.md

For all projects use ~/.claude/agents/. Claude delegates by the description field or an @-mention

Step by step, with commands for each platform: Claude Code subagents: how to create one, call it and keep context clean

Questions about podcast-transcriber

How to install podcast-transcriber in Claude Code?

Run npx claude-code-templates@latest --agent ffmpeg-clip-team/podcast-transcriber. Alternatively, place the agent definition directly into .claude/agents/podcast-transcriber.md.

What does podcast-transcriber do?

It automates media extraction and speech transcription, outputting a structured JSON document with timestamps, confidence scores, and speaker labels.

What dependencies does podcast-transcriber require?

The subagent uses Bash, Read, and Write tools in Claude Code. The host system must have ffmpeg and ffprobe installed and reachable in the path.

Similar subagents

All subagents for AI and ML →
prompt-engineer VoltAgent Community This subagent designs, tests, and improves prompts for LLM production systems. Use it when prompts need evaluation, metrics, or cost tracking. 16,078installs prompt-engineer Seth Hobson This subagent designs and tests prompts for LLM features, agent workflows, and system instructions. Use it when prompt structure, safety, or evaluation needs deliberate work. CX Codex 16,078installs ai-engineer VoltAgent Community This subagent helps design AI systems, choose models, build training pipelines, and prepare deployment. Use it when work spans research through production. 7,687installs ai-engineer Seth Hobson This subagent designs LLM applications, RAG systems, and AI agents. Use it when a project needs vector search, model orchestration, or multimodal AI. CX Codex 7,687installs search-specialist Seth Hobson A web research subagent that filters sources and cross-checks facts. Use it for deep research, competitive analysis, and trend work. CX Codex 6,886installs business-analyst Seth Hobson This subagent analyzes business data and helps shape KPIs, forecasts, and financial models. Use it to turn a business question into an analysis plan and recommendations. CX Codex 3,855installs

From the same set804

The whole set →
api-patterns This skill guides API style choices and covers response structure, versioning, and pagination. Use it when planning an API. 491installs obsidian-markdown This skill helps Claude Code create and edit Markdown notes using Obsidian syntax. Use it for wiki-style links, callouts, embeds, and note properties. 490installs neon-expert Get guidance on Neon Serverless Postgres setup, connections, branching, and scaling. The subagent routes schema, auth, and query-diagnosis work to specialists. 484installs deployment-health-monitor Tracks Vercel deployment status on session start and after build or deploy commands. Flags failed builds and calculates deployment success rates. 482installs nextjs-api-tester Inspects Next.js API routes and generates complete test suites. Useful for verifying authentication, payload validation, and errors across App and Pages Router. 479installs statistical-analysis Automates hypothesis testing, assumption verification, and APA-formatted summary drafting. Helpful for researchers processing scientific experimental datasets. 478installs neon-database-architect A subagent for designing Neon schemas, wiring up Drizzle ORM and tuning queries for serverless workloads. 478installs e2e-setup Sets up end-to-end testing in your project, selects a framework like Playwright or Cypress, and prepares CI integration. 477installs

Project sponsors

Companies that keep this analytics open
Gold sponsor
Nutra.Club

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor