www.ultravox.ai Open in urlscan Pro
52.223.52.2  Public Scan

Submitted URL: http://app.fixie.ai/
Effective URL: https://www.ultravox.ai/
Submission: On October 29 via api from US — Scanned from US

Form analysis 1 forms found in the DOM

<form class="framer-1es8hzz"><label class="framer-xzfphn">
    <div class="framer-fvw42o" style="outline:none;display:flex;flex-direction:column;justify-content:flex-start;flex-shrink:0;transform:none" data-framer-component-type="RichTextContainer">
      <p class="framer-text framer-styles-preset-1qrfog3" data-styles-preset="fp8uZJYNW">Name</p>
    </div>
    <div class="framer-form-text-input framer-form-input-wrapper framer-e9k2ao"><input type="text" name="Name" placeholder="Jane Smith" class="framer-form-input framer-form-input-empty" value=""></div>
  </label><label class="framer-1h7apl8">
    <div class="framer-1i5giqx" style="outline:none;display:flex;flex-direction:column;justify-content:flex-start;flex-shrink:0;transform:none" data-framer-component-type="RichTextContainer">
      <p class="framer-text framer-styles-preset-1qrfog3" data-styles-preset="fp8uZJYNW">Email</p>
    </div>
    <div class="framer-form-text-input framer-form-input-wrapper framer-1y707a2"><input type="email" name="Email" placeholder="jane@framer.com" class="framer-form-input framer-form-input-empty" value=""></div>
  </label><label class="framer-4j5kze">
    <div class="framer-1s9hd9k" style="outline:none;display:flex;flex-direction:column;justify-content:flex-start;flex-shrink:0;transform:none" data-framer-component-type="RichTextContainer">
      <p class="framer-text framer-styles-preset-1qrfog3" data-styles-preset="fp8uZJYNW">Email</p>
    </div>
    <div class="framer-form-text-input framer-form-input-wrapper framer-u9az1k"><textarea name="Email" placeholder="Hey! I’m interested in learning more about UltraVox!" class="framer-form-input"></textarea></div>
  </label>
  <div class="ssr-variant hidden-1fh1kti hidden-1qf2dxn">
    <div class="framer-4ruyk5-container"><button type="submit" class="framer-RTS0V framer-1dzdwg framer-v-1dzdwg" data-border="true" data-framer-name="Default" data-reset="button"
        style="--border-bottom-width:1px;--border-color:var(--token-6e03eac8-db1a-4a11-a0bf-a8a40fe20efd, rgb(255, 255, 255));--border-left-width:1px;--border-right-width:1px;--border-style:solid;--border-top-width:1px;background-color:var(--token-9d53dc8b-7896-4035-9307-141a11c6c001, rgb(0, 0, 0));border-bottom-left-radius:5px;border-bottom-right-radius:5px;border-top-left-radius:5px;border-top-right-radius:5px;height:100%;width:100%;opacity:1"
        tabindex="0">
        <div class="framer-1x2cq5s"
          style="outline: none; display: flex; flex-direction: column; justify-content: flex-start; flex-shrink: 0; --extracted-r6o4lv: rgb(255, 255, 255); --framer-link-text-color: rgb(0, 153, 255); --framer-link-text-decoration: underline; transform: none; opacity: 1;"
          data-framer-component-type="RichTextContainer">
          <p style="--font-selector:SW50ZXItU2VtaUJvbGQ=;--framer-font-family:&quot;Inter&quot;, &quot;Inter Placeholder&quot;, sans-serif;--framer-font-size:14px;--framer-font-weight:600;--framer-text-color:var(--extracted-r6o4lv, rgb(255, 255, 255))"
            class="framer-text">Submit</p>
        </div>
      </button></div>
  </div>
</form>

Text Content

ULTRAVOX

Models

API Docs

About Us

Get Started






AI THAT COMMUNICATES JUST LIKE WE DO

Ultravox is an open-source Speech Language Model (SLM) trained to understand
speech naturally, just like humans do. Say goodbye to awkward pauses, slow
response times, and robotic speech — Ultravox delivers smooth, real-time
communication.

Get in touch

TRY IT OUT

ver 0.4


LEARN MORE ABOUT ULTRAVOX BY TALKING TO IT.

Try a demo

or call 1 844-741-5700





THE FUTURE OF AI SPEECH IS HERE

Experience the cutting-edge of AI speech with Ultravox, where technology meets
human interaction; creating fluid, natural conversations on every medium

BEYOND SPEECH RECOGNITION

Ultravox is an advanced LLM that processes speech directly, without conversion
to text. This enables much more natural and fluid conversations.

WEB OR VOIP READY

Seamlessly integrate Ultravox into your web, native app, or phone-based products
with minimal effort. It comes with SDKs for all major languages and built-in
Twilio support.

MULTI-LINGUAL BY DEFAULT

Ultravox is fluent in all major languages, and easily adaptable support new
languages or accents, ensuring smooth communication across diverse audiences.

BYOM (BRING YOUR OWN MODEL)

Ultravox gives you the flexibility to work with any open-source model, even your
own fine-tuned models.


FAST, ACCURATE, SMART. PICK THREE.

Unlike other voice-based systems, Ultravox integrates speech recognition
directly, without relying on transforming speech into text.  This makes Ultravox
faster, more reliable, and more natural.

Ultravox

Understanding speech directly means there are fewer moving parts. This means
much faster and much more consistent response times than the Legacy Component
System.

Legacy Component Systems

The current industry standard is a cascaded pipeline of services strung together
to give the illusion of a seamless experience. This means it's slower, more
brittle, and unable to capture the nuances of human speech.

BENCHMARKS

COVOST2 TRANSLATION

Our primary method of evaluation is zero-shot speech translation, measured by
BLEU, as a proxy or general instruction-following capability (the higher the
number the better)

En - De

25.47



En - Ca

27.46



En - Ar

28.07



Ru - En

38.96



Es - En

37.11



Zh - En

10.08




CUSTOMIZE IT, THEN RUN IT ANYWHERE (EVEN ON-PREM)

Whether it's adding support for additional languages, fine-tuning on your own
datasets, or creating unique and custom voices — Ultravox can be fully
customized to your needs.

Ultravax can also be deployed directly in your own cloud.

Get in Touch


ALL THE BASICS, PLUS SOME

We know some of these are expected, but we want you to know we cover the basics:

Function Calling

Fine-tunable

Interruptions

Custom Voices & Voice Cloning Support

RAG Support

Works with existing text-based prompts

Multi-lingual

High Quality Speech


PEOPLE ARE NOTICING

They can't stop saying nice things about us *blushes*


JOE HEITZEBERG

@jheitzeb

Wow! Ultravox is an *open source* speech to speech model — understands
non-textual speech elements — paralinguistic information. @juberti just showed
how it can pick up on tone, pauses, and more! @AITinkerers Seattle @FixieAI


BHARAT

@that_anokha_boy

ultravox is prolly most underrated project yall should checkout. i checked
sarvam's shuka's code that is also inspired by ultravox.


SIMON WILLISON

@simonw

I just spent some time with the voice demo of Ultravox at
https://ai.town/ultravox and it really impressed me - openly licensed
multi-modal audio model (like GPT-4o) based on Llama 3, and you can talk to it
in your browser


GET IN TOUCH

We'd love to learn more about your use case and how we can help

Name



Email



Email



Submit

PREFER DIRECT EMAIL? WE'RE HERE:

hello@fixie.ai

About Us

Contact

Careers

Terms and Service

© 2024 Fixie

hello@fixie.ai