MCP / Models / Voice, music and sound
Stable Audio 3 Medium Inpainting MCP: redo part of a track
Stable Audio 3 Medium Inpainting regenerates the part of your track you mark, from a text prompt, and keeps the rest. Run it from Claude Code, Codex, Cursor or any MCP client through one FlyMy.AI MCP, or call its API.

$ YOUR NEXT RUN
Use Stable Audio 3 Medium Inpainting in your assistant
Paste this prompt into Claude Code, Codex, Cursor or any agent. It reads the guide and helps you connect.
Read https://flymy.ai/skill.md and https://flymy.ai/mcp/models/stable-audio-3-medium-audio-inpainting.md. Help me connect the FlyMy.AI MCP to this assistant, then run Stable Audio 3 Medium Inpainting (flymyai/stable-audio-3-medium-audio-inpainting) for this task: Replace seconds 20 to 30 of the music track I attach with a calmer piano passage using Stable Audio 3 Medium Inpainting.
What Stable Audio 3 Medium Inpainting does
Send audio, your track as a link or an upload, and mark the part to regenerate with mask_start_seconds and mask_end_seconds, both required, in seconds from the start of the track (up to 380); the end must come after the start and everything outside the part is kept. Say in prompt what should play there, for example a calmer passage with soft piano, and in negative_prompt what to keep out. seed repeats a result and num_inference_steps (1 to 100, 8 by default) rarely needs changing on this distilled model; output_format is mp3 (the default, 192 kbit/s), wav, flac, ogg, opus, m4a or aac. Outputs: audio, the track with the part regenerated, and seed. It is Stability AI's audio-editing model with 1.4 billion parameters: use it to replace a section, rework a passage or fill a gap.
It is billed at one flat price per run, and it works on one part per request. It does not make a track from text alone (Stable Audio 3 Medium does), change the parts outside the marked one or add audio before or after your track (Stable Audio 3 Medium Outpainting does).
Send only audio you have the right to use.
Stable Audio 3 Medium Inpainting inputs
Every input of flymyai/stable-audio-3-medium-audio-inpainting as its live schema lists them. Returns audio (array), seed (string).
| Input | Type, values and default |
|---|---|
# prompt | string required What should play in the regenerated part of the track, e.g. a calmer passage with soft piano |
# audio | file required Allowed: audio file, as a URL or upload The track to edit (only the marked part is regenerated), a link or an upload; send only audio you have the right to use |
# mask_start_seconds | number required Allowed: 0 to 380 Where the part to regenerate starts, in seconds from the start of your audio (0-380); everything outside the part is kept |
# mask_end_seconds | number required Allowed: 0 to 380 Where the part to regenerate ends, in seconds from the start of your audio (0-380), after its start |
# negative_prompt | string optional Qualities to keep out of the music, e.g. distortion or noise |
# seed | integer optional Allowed: 0 to 2147483647 Seed for a repeatable result |
# num_inference_steps | integer optional Allowed: 1 to 100 Default: 8 Sampling steps, 1-100 (8 by default): this distilled model gains little from more |
# output_format | string optional Allowed: mp3, wav, flac, ogg, opus, m4a, aac Default: mp3 File format: mp3 (the default, 192 kbit/s), lossless wav or flac, or ogg, opus, m4a or aac |
Ask your agent
Requests to paste as they are, once the FlyMy.AI MCP is connected.
flymyai/stable-audio-3-medium-audio-inpaintingflymyai/stable-audio-3-medium-audio-inpaintingflymyai/stable-audio-3-medium-audio-inpaintingStable Audio 3 Medium Inpainting price
$0.0442 per run. A run at the default settings costs $0.0442. Billed to your FlyMy.AI balance; no seats, no subscription and no minimum.
Call Stable Audio 3 Medium Inpainting from code
The same model, from an agent or from your own code. Keys stay in your FlyMy.AI account.
From an agent, through the MCP
The agent calls get_model_schema, then run_model with:
{
"endpoint_id": "flymyai/stable-audio-3-medium-audio-inpainting",
"input": {
"prompt": "A calmer passage with soft piano",
"audio": "https://example.com/voice.mp3",
"mask_start_seconds": "4",
"mask_end_seconds": "8"
}
}From your code, over HTTP
Form fields, not JSON; files go as uploads or public URLs. The answer is a prediction_id; read the result at https://api.flymy.ai/api/v1/flymyai/stable-audio-3-medium-audio-inpainting/predict/async/result/?request_id=<prediction_id>.
curl -X POST https://api.flymy.ai/api/v1/flymyai/stable-audio-3-medium-audio-inpainting/predict/async/ \
-H "X-API-KEY: $FLYMYAI_API_KEY" \
-F 'prompt=A calmer passage with soft piano' \
-F "audio=@voice.mp3" \
-F 'mask_start_seconds=4' \
-F 'mask_end_seconds=8'Questions about Stable Audio 3 Medium Inpainting
Do I need a Stability AI API key for Stable Audio 3 Medium Inpainting?
No. Stable Audio 3 Medium Inpainting runs on FlyMy.AI's account, so you need no Stability AI key or plan: sign in to FlyMy.AI once and each run is billed to your FlyMy.AI balance.
How much does Stable Audio 3 Medium Inpainting cost?
$0.0442 per run. There is no subscription or minimum; the price comes from FlyMy.AI billing and was checked on 2026-11-18.
How do I use Stable Audio 3 Medium Inpainting in Claude Code, Codex or Cursor?
Add the FlyMy.AI MCP with one command and sign in, then ask in plain words, for example: "Replace seconds 20 to 30 of the music track I attach with a calmer piano passage using Stable Audio 3 Medium Inpainting." Your agent reads the inputs with get_model_schema and runs flymyai/stable-audio-3-medium-audio-inpainting with run_model.
What does Stable Audio 3 Medium Inpainting need as input?
Stable Audio 3 Medium Inpainting requires prompt, audio, mask_start_seconds and mask_end_seconds; it also takes 4 optional inputs, each listed on this page with its allowed values and default.
Can I call Stable Audio 3 Medium Inpainting from my own code?
Yes. Send form fields to https://api.flymy.ai/api/v1/flymyai/stable-audio-3-medium-audio-inpainting/predict/async/ with your FlyMy.AI API key in the X-API-KEY header.
Go to the source
From the FlyMy.AI model catalog of 2026-11-18: inputs from the model's live schema, prices from FlyMy.AI billing. Requests are examples to paste, not recorded runs.





