Dialt

We tune how voice assistants sound, speak and behave.

[Trelis Research @TrelisResearch]

This voice agent was EXTREMELY RUDE!!!

..available now through the https://t.co/gMibMOG1jK api, for approved orgs only.

Why is this useful?
- for training (e.g. simulated customers/patients)
- testing out your production agents

For custom simulations/characters reach out to hello at dialt dot com

[Dialt @dialt_ai]

Voice agents for multispeaker rooms

Live now in our API and Playground

[Trelis Research @TrelisResearch]

@dialt_ai now allows a voice agent to engage in a multispeaker room!

Via UI but also API for integrating into @Zoom , @Google Meet, @boardyai etc…

Demo video coming soon but functionality is live!

[Trelis Research @TrelisResearch]

Today we’re launching Dialt.

Tune how your voice assistants sound, speak and act, down to the model weights.

We serve our own conversational voice models and train them on your data:

• Voice and accent
• Conversational style
• When and how they call your tools

Build a simulated patient who’s reluctant to share, a customer who pushes back, or an assistant that speaks your customers’ dialect.

Try the playground: https://t.co/F0PXcmqAtF
And follow us @dialt_ai

[Trelis Research @TrelisResearch]

We are launching Dialt!

Join us on Wednesday for our official launch!

5 pm Dublin, 12 pm New York, 9 am SF.

Sign-up to attend: https://t.co/ZGx4TrcVXv

[Dialt @dialt_ai]

Quick demo of two ways to handle a caller speaking a different language.

[Trelis Research @TrelisResearch]

Two ways to have a virtual assistant swap languages https://t.co/zm9cTAJGGr

[Dialt @dialt_ai]

New feature - Interactive Voice Design - in beta

[Trelis Research @TrelisResearch]

Interactively design a virtual assistant.

By @dialt_ai .

[Dialt @dialt_ai]

Now available through Pipecat!

[Ronan McGovern @RonanKMcGovern]

Dialt's conversational voice engine is now also available through @pipecat_ai!

If you're using Pipecat, try flipping over to Dialt Fast or Dialt Smart and trying them out.

[Dialt @dialt_ai]

Dialt Fast and Dialt Smart - now with even more consistent fast responses!

[Ronan McGovern @RonanKMcGovern]

Dialt Fast and Dialt Smart models have extended their lead over Gemini 3.8 Live and OpenAI’s GPT Live 1 models, with further improved response times (latency).

This is an internal cross-customer benchmark, but, as we like to say at Dialt…

“The most important benchmark the one you build yourself, for your own application.”

The Dialt API allows you to:

1. Quickly spin-up a benchmark that is bespoke to your use case

2. Measure performance of Dialt vs Gemini vs OpenAI models using that benchmark

3. [Coming soon] Create training data and tune Dialt models to further improve performance. Reach out for more info

[Dialt @dialt_ai]

The MOST important of all benchmarks for voice agents!

[Ronan McGovern @RonanKMcGovern]

What's the MOST important benchmark for voice agents?

It's the one you build yourself, for your own application.

Here's how to do that with Dialt Evals.

[Dialt @dialt_ai]

Our new model, Dialt Fast. Outcompetes Gemini and GPT Live on our internal cross-customer benchmark.

[Ronan McGovern @RonanKMcGovern]

A live, unedited call with Dialt Fast, our real-time voice model.

Faster and more accurate than GPT Live-1 and Gemini 3.8 Live on our internal cross-customer benchmark.

[Dialt @dialt_ai]

These tips apply whatever your approach to building voice agents, @ElevenLabs , @pipecat_ai , @livekit etc.

At Dialt, they are built in as defaults.

More to come soon on how we think about evals.

[Ronan McGovern @RonanKMcGovern]

3 tips for voice agent evals:

1. Test in text mode first. Cheaper, and faster than real time.

2. Use a strong simulated caller. If the caller is weak, you won't know if your assistant or the simulated caller was the problem.

3. Use a strong judge, with clear success criteria and a rubric.

[Dialt @dialt_ai]

@communicating @TrelisResearch cheers Christopher!

[Dialt @dialt_ai]

Introducing Dialt

Dialt offers business-specific real-time voice models.

A real-time voice layer you can deploy quickly and improve on your own data.

In alpha with design partners. Reach out to learn more, or visit https://t.co/Pg3UQYNErA .