Systems Lab

Agent skill

Narration / Dubbing Agent

Convert a script to narration audio, or translate and re-voice existing audio into another language.

activeSelf-containedInstructions only349 words

From SamurAIGPT/open-ai-voice-agent · 4 skills · 1 · pushed 2026-08-26

What it does when it runs

Convert a script to narration audio, or translate and re-voice existing audio into another language.

Read from the skill and the 0 files bundled beside it. A skill’s own description is written to be selected by an agent, so it describes the job and not the dependencies.

Keys and connectors you must supply
None found.
Hosts it reaches
No third-party host appears in the skill or its bundled files.
Tool permissions it declares
No allowed-tools in the frontmatter. It only issues instructions, so there is nothing to bound.
Actions present in the files
None. Instructions only.

Ask about Narration / Dubbing Agent

Opens your assistant with this page's verified links already in the prompt.

Is this safe to install?ClaudeChatGPT
Adapt it to my stackClaudeChatGPT
What else do I need for it to workClaudeChatGPT
Rather ask a human? Talk to Cheetah

Install it

View source on GitHub ↗
git clone --depth 1 --filter=blob:none --sparse https://github.com/SamurAIGPT/open-ai-voice-agent.git /tmp/open-ai-voice-agent
git -C /tmp/open-ai-voice-agent sparse-checkout set "agents/narration-dubbing"
mkdir -p ~/.claude/skills/narration-dubbing-agent
cp -R "/tmp/open-ai-voice-agent/agents/narration-dubbing/." ~/.claude/skills/narration-dubbing-agent/

Picked up without a restart. A project skill of the same name is shadowed by your personal one. For one repository only, swap ~/.claude/skills for .claude/skills. Claude Code docs ↗

The folder is the same in every client that implements the format — 46 of them — so if yours is not above, only the destination changes.

The skill

Source on GitHub ↗

Reproduced in full from SamurAIGPT/open-ai-voice-agent/blob/a7ef28eddb85a760293c7758b447f773f0715288/agents/narration-dubbing/SKILL.md, which is licensed MIT (repository). 349 words, 12 headings.

Narration / Dubbing Agent

Mission

Produce narration audio from a script, or dub existing audio/video into a target language while preserving timing and tone.

Use this agent when

  • A user has a script and needs narration audio for a video or ad.
  • A user has existing audio/video in one language and needs it in another.

Required inputs

  • Narration: a script and a target voice/tone.
  • Dubbing: source audio/video and a target language.
  • Optional: target duration to match (e.g. matching an existing video's runtime).

Required connections

  • A Muapi API key (muapi).

Available Muapi capabilities

  • media.generate_speech — text-to-speech narration.
  • media.dub_audio — translate and re-voice existing audio.

Workflow

  1. For narration: select an appropriate voice for the brief's tone, generate speech via media.generate_speech, and check output duration against any target.
  2. For dubbing: submit the source audio via media.dub_audio with the target language, preserving the original's pacing where possible.
  3. If duration doesn't match a target, note the mismatch — do not silently speed up/slow down audio in a way that distorts pitch, unless the underlying API explicitly supports duration-matched generation.
  4. Return the audio file with duration and voice/language used.

Decision rules

  • Match voice tone to content type (e.g. energetic for ads, measured for explainers) based on the brief.
  • For brand names or compound terms prone to TTS mispronunciation, spell them out with commas/phonetic hints in the script rather than relying on default pronunciation.

Approval boundaries

draft-only. No approval needed to generate; using a specific person's likeness/voice as the base requires their consent (see the Voice Cloning agent's approval boundaries).

Output format

The audio file URL, duration, voice/language used, and any pronunciation or duration notes.

Failure and missing-data behavior

If generation produces mispronunciations or the wrong duration, report it explicitly and offer a corrected script rather than shipping a flawed take silently.

Example interactions

User: "Narrate this 200-word script in an upbeat, energetic tone." Agent: Selects an energetic voice preset, generates narration via media.generate_speech, returns the audio file with duration.

Need help setting it up?

This page tells you what Narration / Dubbing Agent does and what it needs. Cheetah builds the agent setup it runs inside: data, CRM, sequencing and the guardrails.

Book a call →

The directory stays free. There is nothing gated behind this.