Skip to content
Smallest AI

Smallest AI text-to-speech for Bolna AI voice agents

Smallest AI is a text-to-speech provider that gives your Bolna agent fast speech through its Lightning models, built for real-time calls. Pick it when low latency is your main goal, or when you want Indian, British or American accented voices from one Pro model.

How Smallest AI fits in the stack.

  • Best for

    Turning your agent's replies into natural speech.

  • Use this layer when

    You want to choose the voice, language, accent or latency your callers hear.

  • Connects to

    The LLM's replies upstream, and the phone call downstream.

The synthesizer is the
voice layer.

Smallest AI turns the agent's replies into speech, so callers hear the voice you picked.

  1. Telephony

    Phone network

    • Exotel
    • Plivo
    • Twilio
  2. STT

    Listener

    • Deepgram
    • Sarvam AI (STT)
    • Soniox
  3. LLM

    Reasoning

    • OpenAI
    • Anthropic
    • Google Gemini
  4. TTS · You are here

    Voice

    • Smallest AI
  5. Tools

    Actions

    • Cal.com
    • n8n
    • AiSensy

How do I set up Smallest AI with Bolna?

Which Smallest AI models does Bolna support?

ModelWhat it isVoices and accents
lightning_v3.1Lightning v3.1 modelNot stated in the Bolna docs
lightning_v3.1_proPremium Lightning model, 44.1 kHz audio, natural prosody149 Pro voices across Indian, British and American accents

For more detail, see the Smallest setup guide in the Bolna docs.

The Bolna docs do not list a per-language breakdown for Lightning. Check Smallest's own voice catalog before you build a non-English agent.

What can you build with Smallest AI and Bolna?

  • Low-latency support lines

    Use Lightning where quick replies matter more than anything else.

  • Indian-accented English agents

    Pick from Pro voices with Indian accents for callers in India.

  • High-volume outbound campaigns

    Run reminder and notification calls where fast, clear speech keeps each call short.

Other providers in this layer.

See all 12 text-to-speech providers
  • Soniox (TTS)

    Text-to-speech

    Soniox tts-rt-v2 gives your Bolna voice agent real-time streaming speech in 63 languages from one model, with 200 named voices and voice cloning.

  • Amazon Polly

    Text-to-speech

    Amazon Polly gives your Bolna voice agent low-cost text-to-speech with generative, neural and standard engines across a broad range of locales.

  • Azure Text-to-Speech

    Text-to-speech

    Azure Text-to-Speech gives your Bolna voice agent Microsoft's neural voices in many languages, covered by Bolna's flat per-minute rate on the neural model.

Keep exploring the voice stack.

See where Smallest AI fits in your workflow.

Walk through provider choice, stack trade-offs and the exact workflow you want Bolna to automate.

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 supports lightning_v3.1 and lightning_v3.1_pro. The older lightning-v2 and lightning-large models are deprecated.