Synthesizer
Amazon Polly logo

Amazon Polly text-to-speech for Bolna AI voice agents

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

ttssynthesizerpollyawstext-to-speechlow-cost
At a glance

How Amazon Polly 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 Amazon Polly used for in a Bolna voice agent?

Amazon Polly (AWS Polly) is a text-to-speech service from Amazon Web Services that turns your Bolna agent's replies into speech. Bolna's provider guide lists it as the pick for cost-sensitive workloads, with neural voices available and broad locale coverage.

Choose Polly when you run a high volume of calls and cost per minute matters more than having the most expressive voice.

How do I set up Amazon Polly with Bolna?

  1. Open your agent in Agent Studio and go to the Languages tab, or build the agent through the Create Agent API.
  2. Set the synthesizer provider to polly in tools_config.synthesizer.provider.
  3. Pick an engine as the model: generative, neural or standard. Bolna sends this value to Polly as engine.
  4. Set language inside provider_config. It is required for Polly, and leaving it out returns 400 Tools Config > Voice > Language: This field is required.
  5. Resolve a valid voice with the List TTS providers and List voices endpoints before you create the agent, since the voice catalog changes over time.
  6. Turn on stream: true and place a test call.

For the full reference, see the Amazon Polly setup guide in the Bolna docs.

Which Amazon Polly engines does Bolna support?

Model (engine)What it is
generativePolly's generative engine
neuralNeural TTS (NTTS), more natural than standard voices
standardStandard TTS, the cost-effective option for scale

In a multilingual agent, Bolna resolves each language into provider_config.language for Polly automatically, so you can use Polly on more than one language tab.

What can you build with Amazon Polly and Bolna?

High-volume reminder and notification calls. Bolna's decision guide pairs AWS Polly with Deepgram Nova-2 for cost-sensitive, high-volume work. Pair it with Deepgram transcription for outbound reminders and confirmations. See pricing for how voice providers affect your rate.

Multilingual agents on one voice provider. Polly covers many locales. Use it across several language tabs, or mix it with Sarvam for Indian languages where you want native voices.

Simple informational lines. Use the standard engine for scripted, predictable messages such as order status, and switch to neural or generative when a conversation needs a warmer voice.

A budget fallback to premium voices. Run a premium voice like ElevenLabs on customer-facing calls and Polly on internal or bulk campaigns.

FAQ

Amazon Polly on Bolna: frequently asked questions

Yes. Set the synthesizer provider to `polly` and pick one of three engines, `generative`, `neural` or `standard`. Bolna sends the model value to Polly as the engine.

Bolna supports the `generative`, `neural` and `standard` engines. Neural voices sound more natural than standard ones, and standard is the cost-effective option for scale.

Yes. `language` is required inside `provider_config` for `polly`. Leaving it out fails with a 400 error, even if the transcriber already has a language set.

Bolna's provider guide recommends AWS Polly for cost-sensitive, high-volume workloads. For the most natural English voices, the same guide points to ElevenLabs.

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 Amazon Polly fits in your production workflow

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