redub

A command for replacing the spoken voice in an existing video. It extracts the audio, transcribes the words, creates new speech with ElevenLabs, and combines that speech with the video.

In plain words
What is it for?
Use it to choose a default voice, an ElevenLabs voice ID, or a voice from the ElevenLabs library, then produce a redubbed version of the video.
Why use it?
It avoids recreating the video when only the narrator or voice needs to change. The command can work with a standalone video file rather than requiring a particular project structure.

Command for Claude Code

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.

agentmods
npx agentmods add commands/digitalsamba/claude-code-video-toolkit/redub
Clone the repo
git clone --depth 1 https://github.com/digitalsamba/claude-code-video-toolkit

Made for: Claude Code.

Per session 7 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,322 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00007 $0.01322
Opus 5 $0.00003 $0.00661
Sonnet 5 $0.00001 $0.00264
Haiku 4.5 $0.00001 $0.00132

Measured 3d ago against content hash 8168a43a543e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

redub 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 3d ago.

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.

.claude/commands/redub.md · 206 lines

How it starts

The opening of the file, as written. The whole thing — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Redub Video

Replace the voice in an existing video using ElevenLabs transcription + TTS.

This is a utility command - it works on any video file without requiring a project structure.

Pipeline

Input Video → Extract Audio → Transcribe → TTS (new voice) → Replace Audio → Output Video

Entry Point

Step 1: Get Input Video

Ask the user for the input video:

/redub - Replace voice in a video

Enter the path to the video you want to redub:

If user provides a path, verify it exists. If not found, list recent MP4 files:

find . -name "*.mp4" -type f -mtime -7 | head -10

Step 2: Choose Target Voice

Help the user choose a voice. Options:

Option A - Use default voice: Check ELEVENLABS_VOICE_ID env var or toolkit-registry.json config.

Option B - List available voices:

# User can find voices at: https://elevenlabs.io/app/voice-library
# Or use the API to list voices

Option C - User provides voice ID: Ask for the ElevenLabs voice ID directly.

Present as a question:

Which voice should narrate the redubbed video?

1. Use default voice (from .env or registry)
2. Enter a voice ID
3. Help me find a voice (opens ElevenLabs voice library)

Step 3: Transcript Handling

Ask how to handle the transcript:

How should we handle the transcript?

1. Auto-transcribe and generate (no review)
2. Auto-transcribe, let me review before TTS (recommended for accuracy)
3. I have my own transcript file

If option 2: set --save-transcript transcript.txt and pause for review. If option 3: ask for transcript file path.

Step 4: Output Location

Suggest default output path:

Output: {input_stem}_redubbed.mp4

Accept default or enter custom path:

Step 5: Execute

Run the redub tool:

source .venv/bin/activate && uv run tools/redub.py \
  --input "INPUT_PATH" \
  --voice-id "VOICE_ID" \
  --output "OUTPUT_PATH" \
  --json

For transcript review workflow:

# Step 1: Transcribe only
source .venv/bin/activate && uv run tools/redub.py \
  --input "INPUT_PATH" \
  --voice-id "VOICE_ID" \
  --output "OUTPUT_PATH" \
  --save-transcript transcript.txt \
  --dry-run

# Show transcript to user, let them edit
# Step 2: After approval, run with edited transcript
source .venv/bin/activate && uv run tools/redub.py \
  --input "INPUT_PATH" \
  --voice-id "VOICE_ID" \
  --output "OUTPUT_PATH" \
  --transcript transcript.txt \
  --json

Read the full file on GitHub · 206 lines

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. 3d ago First seen · 206 lines · 7 tokens per session scan A 8168a43a543e

Subscribe to this mod's changes

redub is a command published in the GitHub repository digitalsamba/claude-code-video-toolkit (2,035 stars, last pushed 2d ago), licensed MIT. It adds 7 tokens to every session and 1,322 once invoked, about $0.0000 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.