How to Use VEED Clean Audio in Hermes
VEED Clean Audio removes background noise from recorded speech while retaining quiet and distant words. Use it for interviews, podcasts, and voiceovers; it returns mono audio with the original duration.
Prompts to try with VEED Clean Audio in Hermes
Copy an example into Hermes, or ask in your own words.
Every weekday, use VEED Clean Audio on newly submitted course narration. Return FLAC copies, keep the originals, and set the same loudness target for every lesson.
Each morning, use VEED Clean Audio on new interview recordings. Process only recordings within 30 minutes and 512 MB, and list any that need splitting.
Every Friday, use VEED Clean Audio to prepare WAV copies of new podcast dialogue recordings. Keep the original recordings for listening comparisons.
Each evening, use VEED Clean Audio on new speech samples intended for lip-sync. Keep the original mixes and mark the cleaned copies for review.
Every Monday, use VEED Clean Audio to create gentler cleanup samples from new voiceovers. Leave more room sound beneath the speech and hold the full recordings for my review.
How to set up VEED Clean Audio in Hermes
Pick the way that suits you. Each takes about two minutes.
Use the Spiral skill
- Send Hermes this message
Your agent reads Spiral's skill and sets itself up.
set up https://spiral.ai/SKILL.md
- Sign in or paste a key
Approve Spiral in the browser, or give the agent a key from the console.
Use Spiral's MCP server
- Add the server and sign in
Hermes opens your browser: sign in to Spiral and click Authorize. No API key. When Hermes asks Enable all tools? \[Y/n/select], answer Y: n cancels without saving the server, and select hides the tools you leave out.
hermes mcp add spiral \ --url https://api.spiral.ai/mcp \ --auth oauth \ --connect-timeout 300
- Check it
In a chat that was already open, run /reload-mcp.
hermes mcp list hermes mcp test spiral
Use the Spiral CLI
- Install and sign in
Installs the Spiral CLI, signs you in and adds its skill to your coding agents.
npx -y spiral-cli@latest init
Call the Spiral API
- Create an API key
In the console, under API keys.
- Run VEED Clean Audio
One request; the result comes back by polling or a webhook.
curl https://api.spiral.ai/v1/runs \ -H "Authorization: Bearer $SPIRAL_API_KEY" \ -H "Content-Type: application/json" \ -H "Idempotency-Key: $(uuidgen)" \ -d '{ "provider": "fal", "model": "veed/clean-audio", "input": { "audio_url": "https://v3b.fal.media/files/b/0aaaa91c/5KspxZ3psz3KmDvSeYVk__noisy_example.m4a" } }'
Then paste one of the prompts above: Hermes finds VEED Clean Audio on Spiral, shows the price and runs it.
VEED Clean Audio providers and prices
Spiral runs VEED Clean Audio through fal. Open a card for today's price, with every fee included.
Settings you can ask for
VEED Clean Audio works from your audio. Ask Hermes for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Strength | 0 to 1 | 0.874 | How much of the original is allowed to remain under speech: the suppression floor is 1 - strength (the default 0.874 is the validated -18 dB). Lower keeps more room tone behind the voice; silence between words is always fully cleaned. |
| Target loudness (LUFS) | -40 to -8 | -19 | Integrated loudness of the output (ITU-R BS.1770). The default -19 LUFS is the level the VEED editor delivers; true peak is capped at -1.1 dBTP. Pass null through the API to skip loudness normalization and keep the input level. |
| Output format | flac or wav | flac | Container for the 48 kHz mono 16-bit output. FLAC is lossless at about half the size of WAV. |
Every API field of VEED Clean Audio is on its tool page: open its card above.
What can you do with VEED Clean Audio in Hermes?
Prepare cleaned speech copies of newly received recordings on a schedule. Keep originals for review and apply the same loudness target to clips intended to play together.
Interview cleanup
Reduce room noise behind an interview, then review quiet answers against the original before editing.
Podcast dialogue
Clean spoken podcast segments and use a consistent loudness target across recordings that play back to back.
Course narration
Reduce air conditioning hum in recorded lessons. Try lower cleanup strength when retaining some room sound makes the narration sound more natural.
Outdoor spoken reports
Reduce wind and traffic behind recorded speech, then check whether words remain clear before using the result.
Lip-sync audio preparation
Remove background music and noise from a speech recording before giving it to a lip-sync model that requests clean speech.
Voice cloning sample preparation
Prepare a speech sample without background noise or music for a voice cloning service that requires clean recordings.
Dubbing preparation
Clean recorded dialogue before a dubbing stage that needs isolated speech. Keep the original sound mix for later editing.
More on VEED Clean Audio and Hermes
Overview
VEED Clean Audio in other agents
Questions about VEED Clean Audio in Hermes
Can Hermes use VEED Clean Audio?
Yes. Add Spiral to Hermes as an MCP server, and Hermes can find and run VEED Clean Audio like any built-in tool.
How much does VEED Clean Audio cost in Hermes?
Up to $0.01625 per run at the default inputs for 60 seconds of input. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Hermes plan is separate.
Do I need a fal account to use VEED Clean Audio in Hermes?
No. Spiral runs VEED Clean Audio on its own fal account. You sign in to Spiral once and never paste a key.
How long does it take to set up VEED Clean Audio in Hermes?
About two minutes: add the server and sign in, then check it.
Does Hermes wait while VEED Clean Audio runs?
VEED Clean Audio runs in the background. Hermes starts the run, checks on it and gives you the audio when it's ready.
What noise can VEED Clean Audio reduce?
It targets background sounds such as wind, air conditioning hum, traffic, static, and echo. It also removes background music and sound effects, so keep the original when those sounds matter.
How long can a recording be?
Each recording can be up to 30 minutes long and 512 MB. Split longer recordings into sections before cleaning them.
Does VEED Clean Audio preserve stereo sound?
The result is mono, so it does not preserve stereo separation. Output is 48 kHz, 16-bit audio with the same duration as the original recording.
Which languages does VEED Clean Audio support?
VEED says it works with recorded speech in any language.
What should I change if the voice sounds thin or processed?
Lower the cleanup strength to leave more room sound beneath the speech. Compare a short section with the original before applying that choice to the full recording.
Start using VEED Clean Audio in Hermes
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into Hermes:
set up https://spiral.ai/SKILL.md


