The tool can add macro-level appropriate ambience, such as forest and bird background audio, but it can also miscalibrate scale so a small bird is rendered with a "giant creature"-sounding chirp.
What was measured
Scene-Sound Relevance
The generated effect matches what is visually happening on screen.
decisive for this rankingtransformation
This directly tests whether the sound effect matches the scene, which is the main reason a user chooses this tool. (3 of 3 judges)
What was given, what came back
Test input: Bird/Nature Video · video · group: auto-sfx-video-generation
Input — what we sent
Input not captured
This run recorded no prompt or input file for the test, so we cannot show you what produced the result below. Capture gaps are tracked, not hidden.
A video featuring a bird in frame, used to test whether generated chirping or ambient sounds sync to the specific animal and movement shown on screen.
Why this input is hard
- · sync accuracy to a visible subject
- · nature/animal sound matching
- · avoiding generic ambience that ignores timing
- · scene-specific audio generation
Also checked on this input — same tool, 1 other criterion
Provenance
- Observation
- 9e5ee9c7-1f4c-4a91-92e6-0f38876193d7
- Evidence run
- 90451942-9055-4e8c-85e6-17c773437ed7
- Study
- Automatically Add Relevant Sound Effects to Videos
- Research task
- 86b84w3x5
- Tested at
- not recorded
- Source
- first-party
- Evidence state
- verified
- Proof shown
- input + output shown
- Cost / latency
- not captured
- Repeat run
- not captured
- Tester
- not captured
The last three rows are honest blanks, not placeholders — our capture has no field for them yet.
Query this
get_evidence({
tool: "fine-voice",
scenario: "auto-sfx-video-generation"
})MCP · mcp.aidemos.com/api/mcp
Free with attribution.
Same input, same check — 2 other tools
measured on Scene-Sound Relevance
This evidence is published in
Real inputs and real outputs, no retouching · every cell queryable via API & MCP · aidemos.com