MCP / Models / Voice, music and sound
Mirelo SFX 2.0 Video to Audio MCP: soundtracks for a video
Mirelo SFX 2.0 watches your video and generates synchronized sound effects, foley and ambience for it, returned as audio files without the video. Run it from Claude Code, Codex, Cursor or any MCP client through one FlyMy.AI MCP, or call its API.

$ YOUR NEXT RUN
Use Mirelo SFX 2.0 Video to Audio 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/mirelo-sfx-2-0-video-to-audio.md. Help me connect the FlyMy.AI MCP to this assistant, then run Mirelo SFX 2.0 Video to Audio (flymyai/mirelo-sfx-2_0-video-to-audio) for this task: Make synchronized sound effects and ambience for the silent clip I attach with Mirelo SFX 2.0 Video to Audio.
What Mirelo SFX 2.0 Video to Audio does
Send video, an MP4 or MOV of 1 to 600 seconds (a fragmented MP4 is refused). text_prompt names sounds the picture does not show and negative_prompt what to keep out; preserve_speech (on by default) builds the soundtrack around the speech of the video; duration asks for fewer seconds than the video and num_samples for one to four variations; upload_audio_format picks WAV, MP3, AAC or FLAC. Outputs: audio, one file per variation, and speech when return_speech is on. It is billed by the seconds of sound per variation, rounded up. It does not mix the sound into the video and makes no music.
Mirelo SFX 2.0 Video to Audio inputs
Every input of flymyai/mirelo-sfx-2_0-video-to-audio as its live schema lists them. Returns audio (array), speech (array).
| Input | Type, values and default |
|---|---|
# video | file required Allowed: video file, as a URL or upload The video to add sound to: an MP4 or MOV file of 1 to 600 seconds, a link or an upload; a fragmented MP4 is refused. The sound runs to its end: $0.015 a second of it (or of duration, if shorter) for each variation, in whole seconds rounded up |
# text_prompt | string optional Optional: sounds the picture does not show, such as off-screen sirens or an ambience bed (up to 2000 characters) |
# negative_prompt | string optional Sounds to keep out, e.g. music, crowd noise (up to 1000 characters) |
# preserve_speech | boolean optional Default: true Keep the speech of the video and build the soundtrack around it; off makes sound effects only |
# duration | integer optional Allowed: 1 to 600 Default: 600 The most seconds of sound, 1-600: 600 (the default) covers the whole video; a smaller number makes less sound and costs less |
# num_samples | integer optional Allowed: 1 to 4 Default: 1 How many variations of the soundtrack, 1-4; each one is billed |
# seed | integer optional Allowed: 0 to 2147483647 Seed for the generation; the same seed repeats a result |
# upload_audio_format | string optional Allowed: wav, mp3, aac, flac Default: wav File format: wav, mp3, aac or flac |
# return_speech | boolean optional Default: false Also return the separated speech of the video as its own file (not billed) |
Ask your agent
Requests to paste as they are, once the FlyMy.AI MCP is connected.
flymyai/mirelo-sfx-2_0-video-to-audioflymyai/mirelo-sfx-2_0-video-to-audioflymyai/mirelo-sfx-2_0-video-to-audioMirelo SFX 2.0 Video to Audio price
From $0.015 per run, depending on the length of the video you send, duration and num_samples. A 10-second video costs $0.15 with the default settings. A run at the default settings costs $0.15. A run costs $0.015 to $36.00, depending on video and duration and num_samples. Billed to your FlyMy.AI balance; no seats, no subscription and no minimum.
Call Mirelo SFX 2.0 Video to Audio 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/mirelo-sfx-2_0-video-to-audio",
"input": {
"video": "https://example.com/clip.mp4"
}
}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/mirelo-sfx-2_0-video-to-audio/predict/async/result/?request_id=<prediction_id>.
curl -X POST https://api.flymy.ai/api/v1/flymyai/mirelo-sfx-2_0-video-to-audio/predict/async/ \
-H "X-API-KEY: $FLYMYAI_API_KEY" \
-F "video=@clip.mp4"Questions about Mirelo SFX 2.0 Video to Audio
Do I need a Mirelo API key for Mirelo SFX 2.0 Video to Audio?
No. Mirelo SFX 2.0 Video to Audio runs on FlyMy.AI's account, so you need no Mirelo key or plan: sign in to FlyMy.AI once and each run is billed to your FlyMy.AI balance.
How much does Mirelo SFX 2.0 Video to Audio cost?
From $0.015 per run, depending on the length of the video you send, duration and num_samples. A 10-second video costs $0.15 with the default settings. There is no subscription or minimum; the price comes from FlyMy.AI billing and was checked on 2026-11-18.
How do I use Mirelo SFX 2.0 Video to Audio in Claude Code, Codex or Cursor?
Add the FlyMy.AI MCP with one command and sign in, then ask in plain words, for example: "Make synchronized sound effects and ambience for the silent clip I attach with Mirelo SFX 2.0 Video to Audio." Your agent reads the inputs with get_model_schema and runs flymyai/mirelo-sfx-2_0-video-to-audio with run_model.
What does Mirelo SFX 2.0 Video to Audio need as input?
Mirelo SFX 2.0 Video to Audio requires video; it also takes 8 optional inputs, each listed on this page with its allowed values and default.
Can I call Mirelo SFX 2.0 Video to Audio from my own code?
Yes. Send form fields to https://api.flymy.ai/api/v1/flymyai/mirelo-sfx-2_0-video-to-audio/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.





