Synthesizer
Maya logo

Maya text-to-speech for Bolna AI voice agents

Maya gives your Bolna voice agent native-sounding text-to-speech in 10 Indian languages plus Indian English, with two voices and mid-call language switching.

Book a DemoBolna Docs
ttssynthesizermayaindiaregional-languagesmultilingual
Official Documentation
At a glance

How Maya 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 Maya used for in a Bolna voice agent?

Maya, from Maya Research, is a text-to-speech provider built for Indian languages, and in Bolna its Maya 2 Native model speaks your agent's replies in 11 languages with two voices. Both voices, Ananya and Arjun, cover every supported language.

Pick it when you need one voice provider for many Indian languages and want the agent to switch language mid-call without reconnecting.

How do I set up Maya 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 maya and the model to Maya 2 Native.
  3. Set voice to Ananya (female, the default) or Arjun (male).
  4. Set language to a code such as hi or ta, or auto to let Maya detect it per utterance. It defaults to en.
  5. Turn on stream: true and keep buffer_size at the default of 400 characters.

Region-qualified codes like hi-IN are trimmed to hi automatically. For the full reference, see the Maya setup guide in the Bolna docs.

Which languages and voices does Maya support on Bolna?

languageLanguage
hiHindi
bnBengali
guGujarati
knKannada
mlMalayalam
mrMarathi
orOdia
paPunjabi
taTamil
teTelugu
enIndian English
autoMaya detects the language per utterance

Voices: Ananya (female) and Arjun (male). Voice and language are chosen independently.

What can you build with Maya and Bolna?

Regional-language outreach. Run collections, reminders or surveys in Odia, Punjabi, Tamil or Telugu from one agent, with the same voice in every language.

Agents that follow the caller's language. Set language to auto, or let Bolna switch it mid-call, so the agent answers in the language the caller speaks. Pair it with Sarvam or Soniox transcription for Indian-language input.

Flat-rate Indian-language calling. Maya is on Bolna's preferred model list, so it stays on the flat per-minute rate. See pricing.

Phone and web from one setup. Bolna converts Maya's 24 kHz audio to 8 kHz mu-law for telephony and keeps it native for web calls.

FAQ

Maya on Bolna: frequently asked questions

Yes. Set the synthesizer provider to `maya`, the model to `Maya 2 Native` and the voice to `Ananya` or `Arjun`. Speech streams over a persistent WebSocket.

Hindi, Bengali, Gujarati, Kannada, Malayalam, Marathi, Odia, Punjabi, Tamil, Telugu and Indian English. You can also set `auto` so Maya detects the language per utterance.

Yes. Bolna sends a language change as a config update over the existing WebSocket, so the call never reconnects.

Yes. Maya is on Bolna's preferred TTS model list, so it is covered by the flat per-minute rate.

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 Maya 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