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

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
generative	Polly's generative engine
neural	Neural TTS (NTTS), more natural than standard voices
standard	Standard 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.