Synthesizer
Smallest AI logo

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

Smallest AI gives your Bolna voice agent low-latency Lightning text-to-speech, with 149 Pro voices in Indian, British and American accents.

Book a DemoBolna Docs
ttssynthesizerlow-latencysmallestedgelightweight
Official Documentation
At a glance

How Smallest AI fits in the stack

Best for

Natural delivery, tone, and response speed on live calls.

Use this layer when

You care about voice quality, expressiveness, or low-latency playback.

Connects to

LLM output upstream and the phone network downstream.

Voice Stack

Text-to-speech is the speaking layer

Text-to-speech is the speaking layer

This provider turns the agent’s response into audio the caller hears. It affects brand perception, caller comfort, and how quickly the next utterance can begin.

TelephonyPhone Network
→
STTListener
→
LLMReasoning
→
TTSVoice
→
ToolsActions

Last updated

What is Smallest AI used for in a Bolna voice agent?

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 do I set up Smallest AI with Bolna?

  1. Connect your Smallest API key at platform.bolna.ai/auth/smallest.
  2. Open your agent in Agent Studio and go to the Languages tab.
  3. In the Voice section, choose Smallest as the provider and pick a Lightning model and voice.
  4. If you use a Pro voice, set the model to lightning_v3.1_pro explicitly. Through the API, set the synthesizer provider to smallest and include language in its config. It is required.

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

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

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.

One provider for listening and speaking. Pair Lightning with Smallest Pulse speech-to-text under a single Smallest account.

High-volume outbound campaigns. Run reminder and notification calls where fast, clear speech keeps each call short.

FAQ

Smallest AI on Bolna: frequently asked questions

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

Pro voices need the model set to lightning_v3.1_pro. Pairing a Pro voice ID with a different model can produce incorrect or hallucinated audio.

Yes. Connect your key at platform.bolna.ai/auth/smallest. The same connection also covers Smallest's Pulse speech-to-text.

Smallest is not on Bolna's preferred model list, so its text-to-speech is billed separately by characters synthesized. With your own key, Smallest bills you directly and you pay Bolna's platform fee.

Related

Other providers in this layer

Synthesizer

Amazon Polly

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

Synthesizer

Azure 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.

Synthesizer

Cartesia

Cartesia gives your Bolna voice agent fast Sonic text-to-speech in 42 languages, including Hindi, with voice cloning and your own API key.

Browse this layer

Keep exploring the voice stack

Browse

Text-to-Speech

Text-to-speech turns your agent responses into spoken audio. Voice quality shapes how callers perceive your brand. Flat, robotic speech kills trust while natural, expressive voices build it. Bolna integrates with the fastest TTS providers so responses sound human and arrive without awkward pauses.

Browse

Telephony

Telephony providers connect your voice agents to the phone network so they can make and receive real calls. Bolna supports managed integrations with major carriers as well as bring-your-own-carrier via SIP trunking, giving you full control over call routing, number provisioning, and cost.

Browse

Large Language Models

The LLM is the brain of your voice agent. It understands what callers say and decides how to respond. Bolna lets you switch between models like GPT-5.4 mini, Claude and DeepSeek by changing the provider and model in your agent LLM settings, so you can tune for speed, cost or reasoning depth.

Browse

Speech-to-Text

Speech-to-text converts what callers say into text that your LLM can process. Transcription accuracy and latency directly affect how natural a conversation feels. Bolna supports streaming STT providers optimized for telephony audio, including specialized models for Indian languages.

Browse

Tools & Workflows

Tools let your voice agents take action during a call, not just talk. Book a calendar slot, look up an order through your own API, push a lead into your CRM, or trigger a multi-step automation in Zapier. These integrations turn voice agents from answering machines into workflow engines.

See where Smallest AI fits in your production workflow

Use the demo to walk through provider selection, stack tradeoffs, and the exact workflow you want Bolna to automate.

Book a DemoRead Bolna Docs