Reply drafts
AI reply suggestions grounded in your content.
Connect your own Google Gemini API key to RolChat and use Gemini models for reply drafts, translation, vision and embeddings - your key, your account.
Categories: Chat models (LLM) Vision Embeddings & search
AI reply suggestions grounded in your content.
Translate messages into the customer's language.
Read tone and detect topic to prioritize.
Tag conversations by topic automatically.
Read screenshots, photos and documents.
Power knowledge base search and routing.
Create a key in your own Google account.
Add the key in RolChat's AI settings and pick which tasks use it.
RolChat routes those tasks to your Google account - no vendor lock-in.
Gemini is split by weight: Flash-Lite for the cheapest work, Flash in the middle, Pro for the heaviest requests.
| Model | Input / 1M tokens | Output / 1M tokens |
|---|---|---|
| Gemini 2.5 Flash-Lite | $0.1 | $0.4 |
| Gemini 3.1 Flash-Lite | $0.25 | $1.50 |
| Gemini 2.5 Flash | $0.3 | $2.50 |
| Gemini 3.5 Flash-Lite | $0.3 | $2.50 |
| Gemini 3.6 Flash | $0.75 | $3.75 |
| Gemini 3.7 Flash | $0.75 | $3.75 |
| Gemini 3.8 Flash | $0.75 | $3.75 |
| Gemini 2.5 Pro | $1.25 | $10.00 |
| Gemini 3.5 Flash | $1.50 | $9.00 |
Provider prices as published on , you are billed by the provider, not by RolChat
Cloud Speech-to-Text handles transcription and Cloud Text-to-Speech reads replies back.
| Model | Does | Per minute |
|---|---|---|
| Google Cloud TTS (Studio voices) | Text to speech | $0.0144 |
| Google Cloud STT v2 | Speech to text | $0.024 |
Provider prices as published on , you are billed by the provider, not by RolChat
This is a bring your own key integration: you connect your own Google account, and RolChat sends the tasks you assign to it. Nothing is resold and nothing is locked in - your key, your usage, your data.
Google covers text and voice from the same account. Gemini handles drafting, translation, tagging and sentiment, while Cloud Speech-to-Text and Cloud Text-to-Speech cover the voice side.
The Flash-Lite and Flash models are priced for the tasks that run constantly, which is what makes them a reasonable default for tagging and routing across a busy inbox. Pro is there for the requests where a longer, more careful answer earns its cost.
Assignments are per task, so nothing forces you to keep text and voice with the same provider. A common setup is Gemini for drafting with a dedicated speech provider for voice messages.
Yes. RolChat connects with your own Google API key, so usage is billed to your account at Google's published rates.
Price per token, and what you would sensibly spend it on. The lighter models are built for high-volume work like tagging; Pro is for the requests where the answer matters more than the rate.
Telephony in RolChat is coming soon. For voice messages in chat, transcription and playback already come from Google Cloud Speech-to-Text and Text-to-Speech, which are part of the same integration.
Bring your own Google account to RolChat and keep full control of your AI - your keys, your data.
Product names, logos and brands shown on this page are the property of their respective owners and are used only to identify the services RolChat can connect to. Their use does not imply any affiliation with or endorsement by them. RolChat connects to these services using your own accounts and API keys.