Voices

Hear the voices on offer, then choose one for your agent and set the languages it answers in.

A voice is three choices: a provider, a model from that provider, and a voice from that model. The voice applies to the whole agent: every step speaks with it.

Providers

ProviderGood forSpeaks
WoiseIndian voices at the lowest price10 Indian languages and English
SarvamNatural Indian voices10 Indian languages and English
SonioxMany voices at a low price60 languages
DeepgramClear, fast US EnglishEnglish only
CartesiaThe most expressive voices44 languages

Woise has two models, each with its own voices. Woise Natural (the default) has Hindi, English and Kannada voices; Woise Classic has voices in ten Indian languages and US English.

Each voice lists how it sounds, the languages it speaks and its gender. Check that it speaks your contacts' languages before you choose it.

Hearing voices

The Voices page lets you browse every provider's voices and play any of them. Type your own line in Text to hear to judge a voice on the words your agent will actually say.

Each play costs a few credits, and the price of the next play shows beside its button. Replaying the same clip is free.

Choosing a voice for an agent

Open the Voice dialog

In the builder, select the voice button in the header. The Voice dialog opens.

Pick a provider and a voice

Choose the provider, the model where there is more than one, and a voice. Play it with your own text before you decide.

Set the languages

Under Languages, choose what the agent Answers in:

  • Same as the contact answers in the language the contact speaks, and follows them if they switch. A language the voice cannot speak gets one it can.
  • One language always answers in the language you pick.
  • My own rule adds your own instruction to the prompt, word for word.

Then pick a Speaking style: Everyday, Professional, or In my words to describe it yourself. The accent comes from the voice; the style changes the words and the tone.

What contacts speak is set with the transcriber, in the AI models dialog.

Save

Select Save voice. The choice is saved to the agent.

Emotions

Some voices can change how they sound, for example happy or calm. When the chosen voice can, Show emotions on calls appears in the dialog. Turn it on and the agent picks a feeling for each reply from what the contact says. How should it show emotion? (optional) lets you steer it, for example Stay calm and kind. Sound happy only when a booking is confirmed. With Cartesia, emotions work in English sentences only.

When the chosen voice cannot change emotion, the dialog names the providers that can.

Next steps

GoalGuide
Decide what the voice saysPrompts
Use a recording for the greeting insteadSteps
Hear the voice on a real callBuilder

Common questions

What is Woise?

Woise lets you build AI agents that answer and make phone calls and chat on your website. You lay out the conversation on a visual canvas, try it in your browser, then connect it to a phone number.

Do I need a phone number to start?

No. You can build and test an agent in the browser without one. When you are ready, connect a phone number and choose which agent answers it.

How does billing work?

You pay for the minutes your agents use, from your credit balance. There are no seat fees and no per-agent fees, so an agent that is not taking calls costs nothing.

Which languages can an agent speak?

Agents can listen and speak in more than 40 languages, including English, Spanish, Hindi, Tamil and Arabic. You pick the language and the voice for each agent.

Can an agent connect to my CRM or calendar?

Yes. An agent can look things up and make changes in 26 apps, such as Salesforce, HubSpot, Google Calendar, Slack and WhatsApp, during the call. You connect each app once.

Do I need engineers to build an agent?

No. Everything is built in a visual editor, so you can create and change an agent without writing code. If your team prefers code, there is also a REST API and an MCP server.

What happens to call recordings and transcripts?

Every call keeps a transcript and its outcome, and audio is only recorded if you turn it on. Only people in your account can see your calls, and your account lives in the region you chose when you signed up.

What do I have to set up or run?

None. We run the speech, the language models, the recordings and the phone connections, and scale them with your call volume. There is nothing for you to set up or keep running.

How do I reach the team?

Email contact@woise.ai, call or WhatsApp +91 83412 34080, or use the form on our contact page. A person reads every message.

Still stuck? Talk to our team.