Share of voice tracking across AI answer engines
Share of voice in AI answers is the share of samples in which a brand appears relative to its competitor set. Because engines are non-deterministic, the honest form of the number is an interval — 34% ±16 points at n=30 — not a single figure.
How it differs by engine
Derived, not parsed: computed from mentions and citations across the sample set.
Google AI Overviews share of voice
Derived across the sample set from mentions and citations combined.
google_ai_overviews
Google AI Mode share of voice
Derived from mentions and citations across the sample set.
google_ai_mode
ChatGPT share of voice
Derived from mentions and citations across the sample set.
chatgpt
Perplexity share of voice
Derived from mentions and citations across the sample set.
perplexity
Microsoft Copilot share of voice
Derived from mentions and citations across the sample set.
copilot
Gemini app share of voice
Derived across the sample set from mentions and citations combined.
gemini
DeepSeek share of voice
Derived across successful samples, with a collection success rate reported alongside.
deepseek
Qwen share of voice
Derived across the sample set, split by prompt intent.
qwen
Doubao share of voice
Derived across successful samples, with a success rate reported alongside.
doubao
Kimi share of voice
Derived across the sample set with length normalisation applied.
kimi
Baidu ERNIE share of voice
Derived across the sample set from mentions and citations combined.
baidu_ernie
Naver share of voice
Derived across the sample set, split by source corpus.
naver
Sampling
What the API returns
{
"engine": "google_ai_overviews",
"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. |
Share of voice FAQ
- What is share of voice tracking?
- Share of voice in AI answers is the share of samples in which a brand appears relative to its competitor set. Because engines are non-deterministic, the honest form of the number is an interval — 34% ±16 points at n=30 — not a single figure.
- How is share of voice sampled?
- 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.
- What does share of voice cost?
- Derived at no extra credit cost, but it scales with n — the interval is bought with samples.
Get share of voice on your prompt set
Track it in the dashboard or pull it in through the API. Send us the prompts, the brands and the markets, and we'll come back with a per-engine coverage plan and the credit arithmetic behind it.