Google Gemini Models for Bolna Voice Agents

Google Gemini models offer large context windows (up to 1M tokens), strong multilingual capability, and competitive latency. gemini-2.5-flash is the stable production recommendation for most agents — good speed-quality balance. The Gemini 3.x series is the newer generation with higher capability.

Quick config

"llm_agent": {
  "agent_type": "simple_llm_agent",
  "agent_flow_type": "streaming",
  "llm_config": {
    "provider": "google",
    "model": "gemini-2.5-flash",
    "max_tokens": 150,
    "temperature": 0.2
  }
}

To use your own Google API key, connect it at platform.bolna.ai/auth/google.

Supported models

Model	Context	Best for	Notes
`gemini-3.7-flash`	1M tokens	Hardest reasoning, agent tasks	Newest generation. Needs `max_tokens` 400+ or replies get cut off
`gemini-3.5-flash`	1M tokens	Complex reasoning, agent tasks	Stable, proven
`gemini-3.1-pro`	1M tokens	Complex tasks, highest quality	Gemini 3 premium model
`gemini-3.1-flash-lite`	1M tokens	Budget, high-volume agents	Fastest in Gemini 3 family
`gemini-2.5-pro`	1M tokens	Advanced reasoning	Gemini 2.5 premium; stable
`gemini-2.5-flash`	1M tokens	Most production voice agents	Recommended — proven, stable, fast
`gemini-2.5-flash-lite`	1M tokens	Cost-sensitive high volume	Cheapest in 2.5 family

Recommendation: Use gemini-2.5-flash for proven production stability. Try gemini-3.5-flash or gemini-3.1-flash-lite for improved performance on newer deployments.

Key settings

Setting	Type	Recommended	Description
`provider`	string	`"google"`	Provider name
`model`	string	`"gemini-2.5-flash"`	Model to use
`max_tokens`	integer	`150`	Cap on response length — keep short for voice
`temperature`	float	`0.2`	Lower = more deterministic
`agent_flow_type`	string	`"streaming"`	Always `"streaming"` for voice

Multilingual support

Gemini models have strong native multilingual capability. For Indian language agents (Hindi, Tamil, Bengali, etc.), Gemini is a good alternative to Sarvam if you need broader LLM capability alongside multilingual handling. Always set the language explicitly in your prompt — Gemini handles it well, but auto-detection adds latency.

FAQ

Gemini 2.5 vs Gemini 3.x — which should I use?

Both are stable. gemini-2.5-flash is the battle-tested choice with predictable performance. gemini-3.5-flash or gemini-3.1-flash-lite offer newer capability and are worth testing — especially for complex reasoning tasks. Switch once you’ve validated quality on your agent.

Why does gemini-3.7-flash return empty or cut-off replies?

Gemini 3.7 Flash always thinks before it answers, and that thinking uses part of the max_tokens budget. At the usual voice setting of 150 there can be little left for the spoken reply, so it comes back cut off or empty. Set max_tokens to 400 or higher for this model. Gemini 2.5 Flash and the other flash models do not need this.

How does Gemini compare to GPT for voice?

Comparable latency. Gemini has an edge on multilingual tasks and large-context scenarios (1M token window). GPT-5.4-mini has a slight edge on English instruction following consistency. Test both on your specific use case.

Can I use my own Google API key?

Yes. Connect at platform.bolna.ai/auth/google. API costs will be charged to your Google account.

LLM Tab — configure LLM in the dashboard
OpenAI — GPT-5 family alternative
Multilingual Support — configure language for your agent
Prompting Guide — write effective prompts for voice

Overview & Evaluation

Concepts

Build & Configure Agents

Voice & Knowledge

Workflows

Integrations

Multilingual Voice Agents

Advanced Capabilities

Graph Agents

Enterprise & Security

Pricing

Google Gemini Models for Bolna Voice Agents

Quick config

Supported models

Key settings

Multilingual support

FAQ

​Quick config

​Supported models

​Key settings

​Multilingual support

​FAQ

​Related

Quick config

Supported models

Key settings

Multilingual support

FAQ

Related