Skip to content

Everything your
voice agent connects to

Pick the phone network, AI models and business tools behind your agent. Book meetings, update your CRM and follow up on WhatsApp, all from a live call.

Collections agent

Hinglish
  1. Starts fromHubSpottrigger
  2. Phone lineExotelcarrier
  3. ListensSarvam AIspeech-to-text
  4. ThinksOpenAILLM
  5. SpeaksSarvam Bulbulvoice
  6. Sends toAiSensyafter the call
New lead received

How it works, one stage
at a time.

A new lead, a due date or a cart left open tells Bolna to call. Your app, Zapier, n8n, Make or a CSV batch sends the request, with details like name or order ID.

Connectors for this stage

Workflows & automation

  • Zapier
  • n8n
  • Make
  • viaSocket

Deployment & procurement

  • AWS Marketplace

All integrations.

Every provider Bolna connects to, grouped by what it does. Bring your own keys, or use Bolna's managed accounts where offered.

Large Language Models

The model that understands the caller and writes every reply.

  • Anthropic

    Anthropic Claude writes your Bolna voice agent's replies. Use claude-sonnet-5 for most agents, or claude-haiku-4-5 for faster, high-volume calls.

    • llm
    • claude
    • anthropic
  • Azure OpenAI

    Azure OpenAI runs GPT models for your Bolna voice agent inside your own Azure account, for teams that need regional data residency and private networking.

    • llm
    • azure
    • enterprise
  • Baseten

    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.

    • llm
    • baseten
    • dedicated-gpu
  • Cerebras

    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.

    • llm
    • cerebras
    • low-latency
  • Custom LLM (OpenAI-compatible)

    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.

    • llm
    • custom-llm
    • openai-compatible
  • DeepSeek

    DeepSeek V4 runs the conversation in a Bolna voice agent at low cost per token. deepseek-v4-flash suits high-volume calls, with a 1M token context window.

    • llm
    • deepseek
    • cost-effective
  • Fireworks AI

    Fireworks AI serves open models to a Bolna voice agent on serverless per-token access or on-demand GPU deployments, connected as an OpenAI-compatible custom LLM.

    • llm
    • fireworks
    • open-models
  • Google Gemini

    Google Gemini runs the conversation in a Bolna voice agent with a 1M token context and strong multilingual skills. gemini-2.5-flash is the recommended default.

    • llm
    • gemini
    • google
  • Gemini Live

    Gemini Live runs a Bolna voice agent on Google's native-audio speech-to-speech model, with 30 prebuilt voices and session resumption for calls past 15 minutes.

    • llm
    • speech-to-speech
    • gemini
  • Groq

    Groq runs Llama and GPT-OSS on fast LPU hardware as the LLM for a Bolna voice agent, shortening the pause between the caller finishing and the agent speaking.

    • llm
    • groq
    • low-latency
  • Modal

    Modal lets you self-host an open-weight LLM with vLLM on serverless GPUs, in a region near your callers, and use it as the model behind a Bolna voice agent.

    • llm
    • modal
    • self-hosted
  • Nebius

    Nebius Token Factory serves open models such as DeepSeek, Qwen and Llama to a Bolna voice agent, with dedicated endpoints in a region you choose for data residency.

    • llm
    • nebius
    • data-residency
  • OpenAI

    OpenAI GPT models write your Bolna voice agent's replies. gpt-5.4-mini is the recommended default, with fast first tokens, function calling and low cost.

    • llm
    • gpt
    • openai
  • OpenAI Realtime

    OpenAI Realtime runs a Bolna voice agent on one speech-to-speech model that hears the caller and speaks back, replacing the separate transcriber, LLM and voice.

    • llm
    • speech-to-speech
    • openai
  • OpenRouter

    OpenRouter gives a Bolna voice agent one API key for models from OpenAI, Anthropic, Google, Mistral, Meta and more. Pick a model and switch any time.

    • llm
    • multi-model
    • openrouter
  • Perplexity

    Perplexity can be the LLM behind a Bolna voice agent. Set the provider to perplexity in the agent config and Bolna routes calls to your chosen Perplexity model.

    • llm
    • search
    • perplexity
  • Simplismart

    Simplismart serves speed-optimised open models to a Bolna voice agent on a shared endpoint or a dedicated deployment, including your own fine-tuned weights.

    • llm
    • simplismart
    • open-models
  • Together AI

    Together AI gives a Bolna voice agent a large serverless catalog of open models such as Llama, Qwen, DeepSeek and MiniMax, billed per token with no provisioning.

    • llm
    • together-ai
    • open-models

What you can build.

  • BFSI & Collections

    EMI reminders that stay compliant

    Confirms identity before any amount is shared and logs the promised pay date.

  • BFSI

    KYC and verification calls

    Walks through each check in order and hands off anything that doesn't match.

  • E-Commerce

    COD order confirmation

    Confirms the order and address before it ships, in the buyer's language.

  • Sales

    Lead qualification

    Calls new leads, asks about budget and timing, and books the right rep.

  • Recruitment

    Candidate screening

    Asks the same screening questions of every candidate, in Tamil, Telugu or English.

  • Customer Support

    First-line support, any hour

    Answers from your knowledge base and transfers the rest with context.

Ready for enterprise.

Secure, compliant and dependable, from the first pilot to full scale.

Contact Sales
  • 99.9% uptime

    Built for your busiest hour. Even if the model fails, the call doesn’t

  • Support and SLAs

    A dedicated team, with service levels shaped around your business

  • Security & compliance

    Data residency, encryption, access controls, full audit trails and more

  • Deploy in your cloud

    Run Bolna in your own cloud or on-premise, your data remains yours

Certified by

  • ISO 27001
  • DPDP compliant

Frequently Asked Questions

Bolna is a conversational voice AI platform for building AI voice agents that answer and make phone calls. Agents hold natural conversations, understand the caller, reply in their language and update your CRM or other systems, so your team can focus on the calls that need a person.