About rw-generate-audio
This skill uses the Runway API to generate and process audio for creators working with speech, sound effects, or audio conversion. A command-line script handles tasks such as text-to-speech, dubbing, and voice isolation, then saves the output to a file.
Key features
- 01Generate speech from text and sound effects
- 02Isolate voices from audio
- 03Dub audio into a selected language
- 04Convert speech and save output files
Use cases
- 01Create narration for a product showcase
- 02Make sound effects for a video or scene
- 03Clean voice from a noisy recording
- 04Dub narration into another language
Install
Copy the command and run it in a terminal.
$
npx skills add https:/After installing, type/rw-generate-audioin Claude Code to confirm it loaded.
Details
From the project READMEGenerate 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
Comments
Markdown supported