What does a Gemini key unlock in BackTalk?

It scores and categorises every new mention with Gemini instead of the free offline scorer, and re-scores existing mentions once. Gemini Flash-Lite is among the cheapest ways to do AI scoring.

How much does it cost?

You're billed by Google at their token rates with no markup. Gemini 2.5 Flash-Lite (~$0.10/$0.40 per million input/output tokens) is the recommended default; a free tier exists with rate limits.

Is this the same as a YouTube Data API key?

No. Both start with AIza… but this is a Google AI Studio (Gemini) key enabled for the Generative Language API, not the YouTube Data API. Use the AI Studio key for sentiment.

Is my API key stored securely?

Your key is encrypted at rest and only decrypted server-side at the moment it's used. The plaintext never reaches your browser and is never logged. Settings shows only a masked hint.

Google (Gemini) key

Bring your own Google Gemini key to score and categorise mentions with Gemini. Without an AI key, BackTalk uses a free offline word-list scorer; a Gemini key upgrades every new signal to AI sentiment, categories, and priority. Gemini's Flash-Lite tier is among the cheapest ways to do it.

What it unlocks

AI sentiment (positive / neutral / negative) instead of the offline lexicon.
Category and priority tagging on each mention.
A one-time background re-score of your existing mentions when you save the key.

Your workspace runs on one AI key at a time. Saving a Gemini key replaces whichever provider was active before.

Get your API key

Open Google AI Studio → API keys and sign in with your Google account.
Choose Create API key (you can attach it to an existing Google Cloud project or let Studio make one).
Copy the key. It starts with AIza….

Note the difference: this is a Google AI Studio (Gemini API) key, not a YouTube Data API key. Both start with AIza… but are enabled for different APIs, so use the AI Studio one here.

Add it in BackTalk

Go to Settings and find the Gemini (Google) card under AI providers.
Pick a model (see below) and paste your AIza… key.
Save. BackTalk sends one tiny test request to confirm the key and model, then stores the key encrypted and starts the background re-score.

Models & cost

Billed by Google directly at their token rates, with no markup from BackTalk. Gemini offers a free tier with rate limits; paid list prices (USD per million input / output tokens):

Gemini 2.5 Flash-Lite: ~$0.10 / $0.40. Fastest and cheapest; the right default for sentiment.
Gemini 3.5 Flash: ~$1.50 / $9. More capable on ambiguous mentions.

Troubleshooting

"The provider rejected that API key." The key is wrong, or the Generative Language API isn't enabled on its project. Recreate it from AI Studio.
"That model isn't available on this key." Region or account restriction. Try Flash-Lite.
Quota / rate-limit errors. The free tier has low per-minute limits; enable billing on the Cloud project for higher throughput.

Your key stays private. It's encrypted at rest and only decrypted server-side when a scoring call runs. It is never returned to your browser and never logged. Settings shows only a masked hint.

Rotating your key: create a new key in Google AI Studio, paste it into Settings to replace the old one, then delete the previous key.