Automated summary
Generates audio content via the Runway API, including text-to-speech, sound effects, voice isolation, dubbing, and voice conversion.
Strengths
- Supports multiple audio generation types
- Simple command-line parameterization
- Variety of preset voices available
- Direct integration with Runway API
Limitations
- Requires a valid Runway API key
- Depends on Runway API availability
- Audio files must be accessible via URL or local path
Best for quickly generating audio files from text or processing existing audio files without a GUI.
Avoid for complex audio production workflows requiring multi-track editing or real-time processing.
Security analysis
SafeThe skill leverages only standard read/write/execute operations via uv run to call the Runway API. There are no destructive commands, no secrets exfiltration, no obfuscation, and no attempts to disable safety controls. It operates within the allowed-tools constraints and directly fulfills its described purpose.
No concerns found
How this analysis is madeExamples
Generate a text-to-speech audio for 'Welcome to our product showcase' and save it as voiceover.mp3 using Runway API.Create a sound effect of thunder rolling across a stormy sky and save it as thunder.mp3.Isolate the voice from the audio file noisy-recording.mp3 and save the clean audio as clean-voice.mp3.name: rw-generate-audio description: "Generate audio using the Runway API via runnable scripts. Supports TTS, sound effects, voice isolation, dubbing, and voice conversion." user-invocable: true allowed-tools: Read, Grep, Glob, Edit, Write, Bash(uv run *), Bash(command -v uv)
Generate Audio
Generate audio directly using the Runway API. Supports text-to-speech, sound effects, voice isolation, dubbing, and speech-to-speech voice conversion.
IMPORTANT: Run scripts from the user's working directory so output files are saved where the user expects.
Usage
uv run scripts/generate_audio.py --type tts --text "Hello world" --filename "greeting.mp3" [--voice-id ID] [--api-key KEY]
Preflight
command -v uvmust succeedRUNWAYML_API_SECRETmust be set, or pass--api-key
Audio Types
| Type | Description | Required Args |
|------|-------------|---------------|
| tts | Text to speech | --text |
| sfx | Sound effect generation | --text |
| isolate | Isolate voice from audio | --audio-url |
| dub | Dub to another language | --audio-url, --target-language |
| sts | Voice conversion | --audio-url |
Parameters
| Param | Description | Default |
|-------|-------------|---------|
| --type | Audio type (required): tts, sfx, isolate, dub, sts | -- |
| --filename | Output filename (required) | -- |
| --text | Text input (for tts and sfx) | -- |
| --audio-url | Audio URL or local path (for isolate, dub, sts) | -- |
| --voice-id | Voice preset (for tts and sts, e.g. Maya, Noah, Leslie) | Maya |
| --target-language | Language code (for dub, e.g. "es") | -- |
| --output-dir | Output directory | cwd |
| --api-key | Runway API key | env RUNWAYML_API_SECRET |
Examples
Text-to-speech:
uv run scripts/generate_audio.py --type tts --text "Welcome to our product showcase" --filename "voiceover.mp3"
Sound effect:
uv run scripts/generate_audio.py --type sfx --text "Thunder rolling across a stormy sky" --filename "thunder.mp3"
Voice isolation:
uv run scripts/generate_audio.py --type isolate --audio-url "noisy-recording.mp3" --filename "clean-voice.mp3"
Speech-to-speech (voice conversion):
uv run scripts/generate_audio.py --type sts --audio-url "recording.mp3" --voice-id Noah --filename "converted.mp3"
Dubbing:
uv run scripts/generate_audio.py --type dub --audio-url "english-narration.mp3" --target-language es --filename "spanish-dub.mp3"
Output
- The script downloads the result and saves it to the specified path
- Script outputs the full path to the saved file
From the file to a first result
The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.
View the source and supporting filesThis download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.
1. Download the file
Download SKILL.mdFrom the root of a test project, save the file as .skill-downloads/generate-audio-mrzxupwp/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.
Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.
mkdir -p '.skill-downloads/generate-audio-mrzxupwp' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/generate-audio-mrzxupwp/download' --output '.skill-downloads/generate-audio-mrzxupwp/SKILL.md.part' && mv '.skill-downloads/generate-audio-mrzxupwp/SKILL.md.part' '.skill-downloads/generate-audio-mrzxupwp/SKILL.md'2. Check prerequisites
Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.
Tools declared by the author (check availability in your agent): Read, Grep, Glob, Edit, Write, Bash(uv run *), Bash(command -v uv)
No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.
The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.
3. Load the skill
After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.
Claude Code
test -f '.skill-downloads/generate-audio-mrzxupwp/SKILL.md' && test -s '.skill-downloads/generate-audio-mrzxupwp/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/rw-generate-audio' && cp -R '.skill-downloads/generate-audio-mrzxupwp' '.claude/skills/rw-generate-audio'OpenSkills
OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.
Official OpenSkills installationopenskills install './.skill-downloads/generate-audio-mrzxupwp'openskills read 'generate-audio-mrzxupwp'Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.
For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.
openskills syncManual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.
4. Try a first task
Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:
Read .skill-downloads/generate-audio-mrzxupwp/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.
Writing Fragments
Content
Mine raw writing fragments through a relentless interview, without imposing structure. Capture ideas, quotes, and leading words for later use.
UI Copywriting & Auditing
Content
Write or audit user-facing UI copy including buttons, errors, empty states, and tooltips across the monorepo, following the design system source of truth.
Music MIDI Extraction
Content
Extracts the MIDI or score from an existing music production via the CogMusic MCP tool and confirms availability.