Gemini app share of voice tracking
Gemini share of voice is the share of samples naming a brand against its competitor set, reported with a 95% interval and split by grounded and ungrounded runs because the two behave differently.
How it renders
Derived across the sample set from mentions and citations combined.
Sampling
This is the field where n matters most. At n=1 the metric is noise; at n=30 the interval is typically tight enough to defend in a client report.
Gotcha
What the API returns
A single collection call against Gemini app for the share of voice field, sampled n times and returned as one object per prompt.
{
"engine": "gemini",
"field": "share_of_voice",
"prompt": "best ai visibility tracking tool",
"country": "GB",
"language": "en",
"n": 30,
"share_of_voice": [
{
"brand": "Nostimates",
"share": 0.34,
"ci95": {
"low": 0.2,
"high": 0.52
},
"n": 30
},
{
"brand": "Competitor",
"share": 0.21,
"ci95": {
"low": 0.1,
"high": 0.38
},
"n": 30
}
]
}Response fields
| Key | Type | Notes |
|---|---|---|
| brand | string | Brand from the configured competitor set. |
| share | float | Point estimate across the sample set. |
| ci95 | object | 95% Wilson interval as { low, high }. |
| n | integer | Samples behind the estimate. |
| delta_prior | float | null | Change against the previous run of the same prompt set. |
What it costs
Derived at no extra credit cost, but it scales with n — the interval is bought with samples.
See credit pricing →Gemini app share of voice FAQ
- Why split grounded and ungrounded share?
- They are different systems. One reflects training data, the other reflects retrieval. Averaging them tells you nothing actionable.
- How many samples does Gemini need?
- More than the anonymous engines. We usually recommend n=40 because grounding variance adds a second source of noise.
Report Gemini share with the caveats built in
We will size the sample your prompt set needs and quote the credits against it.
Other Gemini app data
Across every engine
Compare how share of voice behaves on every engine we track.
Share of voice across all engines →