How to Use SAM Audio in Gemini CLI
Use SAM Audio to extract speech, instruments, or sound effects from a mixed recording by describing the sound. It returns the requested sound and a separate track containing everything else.
Prompts to try with SAM Audio in Gemini CLI
Copy an example into Gemini CLI, or ask in your own words.
Use SAM Audio on assets/interview.wav with the sound description 'speech'. Save both returned tracks beside the original and add an original-versus-extracted playback comparison to our review page.
Use SAM Audio on assets/street.wav to extract 'car honking' with automatic span prediction enabled. Add the extracted sound and remaining audio to the project's listening review.
Use SAM Audio on assets/piano-mix.wav to extract 'piano playing'. Run one comparison with automatic span prediction enabled and one disabled, and prepare both for listening.
Use SAM Audio on assets/podcast.wav to extract 'dog barking'. Put the remaining-audio track in the podcast edit folder and retain the extracted barking for comparison.
Use SAM Audio on assets/song.wav to extract 'singing voice' with three reranking candidates. Save both returned tracks and add a review note asking the editor to check vocal bleed.
How to set up SAM Audio in Gemini CLI
Pick the way that suits you. Each takes about two minutes.
Use Spiral's MCP server
- Add the server
Or add it to ~/.gemini/settings.json yourself:
gemini mcp add --scope user --transport http spiral https://api.spiral.ai/mcp
- Sign in
Start gemini and run:
/mcp auth spiral
- Check it
In Gemini CLI, run /mcp. From your shell:
gemini mcp list
Use the Spiral skill
- Send Gemini CLI 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 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 SAM 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": "fal-ai/sam-audio/separate", "input": { "audio_url": "https://v3b.fal.media/files/b/0a88511f/tUUCI9eDmeC2RqJEOXrZk_assets_avatar_multi_sing_woman.WAV", "prompt": "piano playing" } }'
Then paste one of the prompts above: Gemini CLI finds SAM Audio on Spiral, shows the price and runs it.
SAM Audio providers and prices
Spiral runs SAM Audio through fal. Open a card for today's price, with every fee included.
$0.065 per 30 seconds of audio, at least 30 seconds. Each extra reranking candidate: $0.0325 per 30 seconds.
Settings you can ask for
SAM Audio works from your audio URL and prompt. Ask Gemini CLI for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Predict spans | on or off | off | Automatically predict temporal spans where the target sound occurs. |
| Reranking candidates | 1 to 7 | 1 | Number of candidates to generate and rank. Higher improves quality but increases latency and cost. |
| Acceleration | fast, balanced, or quality | balanced | The acceleration level to use. |
| Max chunk duration | 10 to 60 | 60 | Maximum audio duration (in seconds) to process in a single pass. Longer audio will be chunked with overlap and blended. |
| Chunk overlap | 0 to 30 | 5 | Overlap duration (in seconds) between chunks for crossfade blending. |
| Output format | wav or mp3 | wav | Output audio format. |
Every API field of SAM Audio · Text-Prompted Sound Separation is on its tool page: open its card above.
What can you do with SAM Audio in Gemini CLI?
Extract dialogue, music parts, and sound effects from recordings used in your project. A coding agent can organize the target and remaining-audio tracks into an editing workflow and prepare comparisons for review.
Prepare interview dialogue
Extract speech from a noisy interview recording for a dialogue edit. Compare the extracted speech with the original before replacing the source track.
Remove barking from a podcast
Target the barking and use the remaining-audio track as a podcast editing candidate. Check the moments where barking overlaps speech.
Reduce traffic in outdoor recordings
Separate traffic noise from recorded outdoor audio, then review the remaining track for use beneath the scene.
Study a piano part
Extract piano from a mixed music recording to hear its phrasing more clearly. Treat the result as a listening aid and review passages with overlapping instruments.
Prepare a vocal editing reference
Separate singing from accompaniment for an editing reference. Avoid relying on it to identify one singer within a chorus.
Collect recorded sound effects
Extract a specific event, such as an engine revving or a horn honking, from a location recording for a sound editing session.
Separate music from spoken content
Target background music in a mixed recording and review the remaining track for a speech-focused edit.
More on SAM Audio and Gemini CLI
Overview
SAM Audio in other agents
Questions about SAM Audio in Gemini CLI
Can Gemini CLI use SAM Audio?
Yes. Add Spiral to Gemini CLI as an MCP server, and Gemini CLI can find and run SAM Audio like any built-in tool.
How much does SAM Audio cost in Gemini CLI?
$0.065 per 30 seconds of audio, at least 30 seconds. Each extra reranking candidate: $0.0325 per 30 seconds. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Gemini CLI plan is separate.
Do I need a fal account to use SAM Audio in Gemini CLI?
No. Spiral runs SAM 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 SAM Audio in Gemini CLI?
About two minutes: add the server, then sign in, then check it.
Does Gemini CLI wait while SAM Audio runs?
SAM Audio runs in the background. Gemini CLI starts the run, checks on it and gives you the audio when it's ready.
What is SAM Audio useful for?
SAM Audio extracts a described sound from a mixed recording. Use it to isolate speech, music, or everyday sound effects for editing and review.
How should I describe the sound I want?
Use a short, lowercase phrase naming the source and its action, such as “piano playing” or “dog barking.” Meta recommends noun or verb phrases that match how the model was trained.
Can SAM Audio remove a sound instead of keeping it?
Yes. Describe the unwanted sound, then use the remaining-audio track, called the residual, for the edit.
What sounds are hardest to separate?
Highly similar sources remain difficult, such as one singer within a chorus or one instrument within an orchestra. Review those results before using them in a finished edit.
When should I try automatic sound timing?
Try it for distinct events, such as barking or honking, so the model predicts when the target occurs. Compare results with it disabled for continuous instrument parts: Meta reported a small decline in professional instrument separation.
Start using SAM Audio in Gemini CLI
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into Gemini CLI:
set up https://spiral.ai/SKILL.md


