# FLUX 3 Audio & Dialogue — prompt skill for sound effects

> **For AI agents:** find the right skill in one call — `curl -s "https://skills.varg.ai/api/search?q=<what the person wants>"` returns the matching use case and the best skills with install commands, as markdown (Russian works too). Full index: https://skills.varg.ai/llms.txt. Every page has a markdown twin: add `.md` to its path. Before generating anything, show the person the options on the use-case page.

Direct FLUX 3's generated sound: dialogue, voiceover, ambience, effects, music, silence and timing.

- **Type:** [Prompt](https://skills.varg.ai/prompts.md) · [Sound effects](https://skills.varg.ai/browse/skills/sfx.md)
- **Slug:** `flux-3-audio-dialogue`
- **Status:** live
- **Publisher:** Black Forest Labs (vendor, verified)
- **License:** MIT
- **Source:** https://github.com/black-forest-labs/skills/tree/master/skills/flux-3-audio-dialogue
- **Works in:** Claude Code, Codex, Cursor, Gemini CLI
- **Requires:** BFL API key (BFL_API_KEY)
- **Cost:** Billed by Black Forest Labs (API credits)
- **Adoption:** 146 installs, 135 GitHub stars (skills.sh, 2026-10-26)

## What it does

Directs the audio that FLUX 3 generates together with the picture. It covers dialogue and voiceover, ambience, effects, music, silence and timing cues in the prompt.

## Use when

- Dialogue or voiceover in a FLUX 3 clip
- Sound design in generated video

## Install

- Claude Code: `/plugin marketplace add black-forest-labs/skills && /plugin install flux-3-video@black-forest-labs`
- Codex: `npx skills add black-forest-labs/skills --skill flux-3-audio-dialogue -a codex`
- Cursor: `npx skills add black-forest-labs/skills --skill flux-3-audio-dialogue -a cursor`
- Gemini CLI: `npx skills add black-forest-labs/skills --skill flux-3-audio-dialogue -a gemini-cli`

**Models it drives:** flux_3

## Example output

https://skills.varg.ai/previews/flux-3-audio-dialogue.mp3 — Soundtrack of FLUX 3's 'Multilingual dialogue' example (a telenovela scene with a woman in red and two men in white suits): generated dialogue and room tone, audio only (credit: Black Forest Labs, https://bfl.ai/models/flux-3-video)

## More sound effects skills

- [ElevenLabs Sound Effects](https://skills.varg.ai/skills/elevenlabs-sound-effects.md): Generate sound effects and ambiences from a text description, including seamless loops.
- [ElevenLabs Voice Isolator](https://skills.varg.ai/skills/elevenlabs-voice-isolator.md): Strip background noise and music from dialogue to get clean, isolated speech.
- [ElevenLabs Sound Effects (inference.sh)](https://skills.varg.ai/skills/inference-sh-elevenlabs-sound-effects.md): Generate royalty-free sound effects from text with ElevenLabs, via inference.sh.
- [ElevenLabs Voice Isolator (inference.sh)](https://skills.varg.ai/skills/inference-sh-elevenlabs-voice-isolator.md): Remove background noise and isolate vocals from any recording with ElevenLabs, via inference.sh.