Healthcare call lines
Appointment scheduling and reminder agents where patient data has to stay in a chosen region.
Azure OpenAI decides how the agent reads intent, picks the next action, calls your tools and writes the reply. It's the decision engine inside the call.
Telephony
Phone network
STT
Listener
LLM · You are here
Reasoning
TTS
Voice
Tools
Actions
Keep the model name in the deployment name.
Connectors for this stage
Large Language Models
| Model | Context | Best for on Bolna | On the flat rate |
|---|---|---|---|
gpt-5.4-miniRecommended | 400K tokens | Most voice agents. Recommended for latency and cost | Included |
gpt-5.4-nano | 400K tokens | Very high volume, simple tasks. Cheapest option | Included |
gpt-5.4 | 1M tokens | General-purpose production agents | |
gpt-5.5 | 1M tokens | Maximum quality on complex tasks | |
gpt-4.1-mini | 1M tokens | Previous generation, if already deployed | Included |
The Azure OpenAI setup guide in the Bolna docs covers the API config, reasoning effort and custom deployment names.
Model availability varies by Azure region, and new models reach Azure a little after OpenAI. Check Microsoft's model availability page for your region.
Appointment scheduling and reminder agents where patient data has to stay in a chosen region.
Account queries and customer support for teams with data residency rules.
Keep the LLM inside the cloud account your security team already manages, with private endpoints. The Bolna docs pair Azure OpenAI with Azure speech-to-text and Azure text-to-speech for enterprise setups.
Deploy to the Azure region closest to your callers and keep reasoning effort at none to cut response time.
Baseten runs open models for a Bolna voice agent through shared Model APIs or your own Truss deployment on dedicated GPUs, including fine-tuned weights.
Cerebras serves gpt-oss-120b at around 3,000 tokens per second as the LLM for a Bolna voice agent, so long replies and tool calls finish almost instantly.
Run a Bolna voice agent on any OpenAI-compatible LLM endpoint, from Groq or Together AI to your own vLLM, SGLang, TGI, Ollama or LiteLLM server.
Understands callers and decides the reply.
18 providersConnects agents to the phone network.
14 providersTurns caller speech into text in real time.
10 providersTurns replies into natural speech.
12 providersLets agents act during and after calls.
7 providersWalk through provider choice, stack trade-offs and the exact workflow you want Bolna to automate.
Secure, compliant and dependable, from the first pilot to full scale.
Built for your busiest hour. Even if the model fails, the call doesn’t
A dedicated team, with service levels shaped around your business
Data residency, encryption, access controls, full audit trails and more
Run Bolna in your own cloud or on-premise, your data remains yours
Certified by
