[happy] Welcome! Bring your applications to life with expressive voices that can whisper secrets, crack jokes, or shout with excitement... Just type your line, pick a voice like Mark or Hades, and hit Generate to play it back.

[sad] Tom broke up with me last week. I'm still feeling lost.

[clear_throat] In a realm where magic flows like rivers and dragons soar through crimson skies, a hero's journey begins with a single step into the unknown.

$5 per million characters—just 5% of competitors’ pricing—with no compromises on quality.

#1 on Hugging Face TTS Arena with clearer speech, lower WER, and higher SIM than leading systems.

12 languages including English, Spanish, French, Korean, and Chinese, all with native-speaker quality.

Create custom voices instantly from 15 seconds of audio, or fine-tune a professionally cloned voice.

Sub-250 ms latency optimized for real-time conversational AI with streaming support.

Add emotion, delivery style, and non-verbal sounds to make speech more expressive and natural.

<div class='p-4' style="width:100%; background-color: white; border-radius: 6px;">
  
  <div class="grid text-xs font-semibold text-gray-700 dark:text-gray-200"
       style="grid-template-columns: 2fr 1fr 1fr;">
    <div class="px-3 py-2  ">Version</div>
    <div class="px-3 py-2 ">Inworld-TTS-1</div>
    <div class="px-3 py-2  ">Inworld-TTS-1-max</div>
  </div>

  
  <div class="grid text-xs   overflow-hidden"
       style="grid-template-columns: 2fr 1fr 1fr;">
    
    <div class="px-3 py-3 font-medium border-b  border-gray-200 ">Radically accessible pricing</div>
    <div class="px-3 py-3 border-b  border-gray-200 ">$5/1M characters <span class="text-gray-500"><br/>(≈ $0.25 per audio-hour)</span></div>
    <div class="px-3 py-3 border-b border-gray-200 ">$10/1M characters <span class="text-gray-500"><br/>(≈ $0.50 per audio-hour)</span></div>

    
    <div class="px-3 py-3 font-medium border-b  border-gray-200 ">Power</div>
    <div class="px-3 py-3 border-b  border-gray-200 ">
      <span style="display:inline-block;width:0.5rem;height:0.5rem;background-color:#0f6a39;border-radius:50%;margin-right:6px;"></span>
      <span style="display:inline-block;width:0.5rem;height:0.5rem;background-color:#0f6a39;border-radius:50%;margin-right:6px;"></span>
      <span style="display:inline-block;width:0.5rem;height:0.5rem;border:1.5px solid #0f6a39;border-radius:50%;"></span>
    </div>
    <div class="px-3 py-3 border-b border-gray-200 ">
      <span style="display:inline-block;width:0.5rem;height:0.5rem;background-color:#0f6a39;border-radius:50%;margin-right:6px;"></span>
      <span style="display:inline-block;width:0.5rem;height:0.5rem;background-color:#0f6a39;border-radius:50%;margin-right:6px;"></span>
      <span style="display:inline-block;width:0.5rem;height:0.5rem;background-color:#0f6a39;border-radius:50%;"></span>
    </div>

    
    <div class="px-3 py-3 font-medium border-b  border-gray-200 ">State-of-the-art quality<br/>(WER & similarity)</div>
    <div class="px-3 py-3 border-b  border-gray-200 "><svg style="fill:var(--new_green_accent); height: 1rem; width:1rem;" xmlns="http://www.w3.org/2000/svg" viewBox="0 0 640 640"><path d="M530.8 134.1C545.1 144.5 548.3 164.5 537.9 178.8L281.9 530.8C276.4 538.4 267.9 543.1 258.5 543.9C249.1 544.7 240 541.2 233.4 534.6L105.4 406.6C92.9 394.1 92.9 373.8 105.4 361.3C117.9 348.8 138.2 348.8 150.7 361.3L252.2 462.8L486.2 141.1C496.6 126.8 516.6 123.6 530.9 134z"/></svg></div>
    <div class="px-3 py-3 border-b border-gray-200 "><svg style="fill:var(--new_green_accent); height: 1rem; width:1rem;" xmlns="http://www.w3.org/2000/svg" viewBox="0 0 640 640"><path d="M530.8 134.1C545.1 144.5 548.3 164.5 537.9 178.8L281.9 530.8C276.4 538.4 267.9 543.1 258.5 543.9C249.1 544.7 240 541.2 233.4 534.6L105.4 406.6C92.9 394.1 92.9 373.8 105.4 361.3C117.9 348.8 138.2 348.8 150.7 361.3L252.2 462.8L486.2 141.1C496.6 126.8 516.6 123.6 530.9 134z"/></svg></div>

    
    <div class="px-3 py-3 font-medium border-b  border-gray-200 ">Real-time latency</div>
    <div class="px-3 py-3 border-b  border-gray-200 "><svg style="fill:var(--new_green_accent); height: 1rem; width:1rem;" xmlns="http://www.w3.org/2000/svg" viewBox="0 0 640 640"><path d="M530.8 134.1C545.1 144.5 548.3 164.5 537.9 178.8L281.9 530.8C276.4 538.4 267.9 543.1 258.5 543.9C249.1 544.7 240 541.2 233.4 534.6L105.4 406.6C92.9 394.1 92.9 373.8 105.4 361.3C117.9 348.8 138.2 348.8 150.7 361.3L252.2 462.8L486.2 141.1C496.6 126.8 516.6 123.6 530.9 134z"/></svg></div>
    <div class="px-3 py-3 border-b border-gray-200 ">
      <span class="inline-flex text-xs ">Soon</span>
    </div>

    
    <div class="px-3 py-3 font-medium border-b  border-gray-200 ">Multilingual <br/>(12 languages)</div>
    <div class="px-3 py-3 border-b  border-gray-200 "><svg style="fill:var(--new_green_accent); height: 1rem; width:1rem;" xmlns="http://www.w3.org/2000/svg" viewBox="0 0 640 640"><path d="M530.8 134.1C545.1 144.5 548.3 164.5 537.9 178.8L281.9 530.8C276.4 538.4 267.9 543.1 258.5 543.9C249.1 544.7 240 541.2 233.4 534.6L105.4 406.6C92.9 394.1 92.9 373.8 105.4 361.3C117.9 348.8 138.2 348.8 150.7 361.3L252.2 462.8L486.2 141.1C496.6 126.8 516.6 123.6 530.9 134z"/></svg></div>
    <div class="px-3 py-3 border-b border-gray-200 "><svg style="fill:var(--new_green_accent); height: 1rem; width:1rem;" xmlns="http://www.w3.org/2000/svg" viewBox="0 0 640 640"><path d="M530.8 134.1C545.1 144.5 548.3 164.5 537.9 178.8L281.9 530.8C276.4 538.4 267.9 543.1 258.5 543.9C249.1 544.7 240 541.2 233.4 534.6L105.4 406.6C92.9 394.1 92.9 373.8 105.4 361.3C117.9 348.8 138.2 348.8 150.7 361.3L252.2 462.8L486.2 141.1C496.6 126.8 516.6 123.6 530.9 134z"/></svg></div>

    
    <div class="px-3 py-3 font-medium border-b  border-gray-200 ">Professional voice cloning <br/>(custom fine-tuning)</div>
    <div class="px-3 py-3 border-b  border-gray-200 "><svg style="fill:var(--new_green_accent); height: 1rem; width:1rem;" xmlns="http://www.w3.org/2000/svg" viewBox="0 0 640 640"><path d="M530.8 134.1C545.1 144.5 548.3 164.5 537.9 178.8L281.9 530.8C276.4 538.4 267.9 543.1 258.5 543.9C249.1 544.7 240 541.2 233.4 534.6L105.4 406.6C92.9 394.1 92.9 373.8 105.4 361.3C117.9 348.8 138.2 348.8 150.7 361.3L252.2 462.8L486.2 141.1C496.6 126.8 516.6 123.6 530.9 134z"/></svg></div>
    <div class="px-3 py-3 border-b border-gray-200 "><svg style="fill:var(--new_green_accent); height: 1rem; width:1rem;" xmlns="http://www.w3.org/2000/svg" viewBox="0 0 640 640"><path d="M530.8 134.1C545.1 144.5 548.3 164.5 537.9 178.8L281.9 530.8C276.4 538.4 267.9 543.1 258.5 543.9C249.1 544.7 240 541.2 233.4 534.6L105.4 406.6C92.9 394.1 92.9 373.8 105.4 361.3C117.9 348.8 138.2 348.8 150.7 361.3L252.2 462.8L486.2 141.1C496.6 126.8 516.6 123.6 530.9 134z"/></svg></div>

    
    <div class="px-3 py-3 font-medium border-b  border-gray-200 ">Embedded safeguards</div>
    <div class="px-3 py-3 border-b  border-gray-200 "><svg style="fill:var(--new_green_accent); height: 1rem; width:1rem;" xmlns="http://www.w3.org/2000/svg" viewBox="0 0 640 640"><path d="M530.8 134.1C545.1 144.5 548.3 164.5 537.9 178.8L281.9 530.8C276.4 538.4 267.9 543.1 258.5 543.9C249.1 544.7 240 541.2 233.4 534.6L105.4 406.6C92.9 394.1 92.9 373.8 105.4 361.3C117.9 348.8 138.2 348.8 150.7 361.3L252.2 462.8L486.2 141.1C496.6 126.8 516.6 123.6 530.9 134z"/></svg></div>
    <div class="px-3 py-3 border-b border-gray-200 "><svg style="fill:var(--new_green_accent); height: 1rem; width:1rem;" xmlns="http://www.w3.org/2000/svg" viewBox="0 0 640 640"><path d="M530.8 134.1C545.1 144.5 548.3 164.5 537.9 178.8L281.9 530.8C276.4 538.4 267.9 543.1 258.5 543.9C249.1 544.7 240 541.2 233.4 534.6L105.4 406.6C92.9 394.1 92.9 373.8 105.4 361.3C117.9 348.8 138.2 348.8 150.7 361.3L252.2 462.8L486.2 141.1C496.6 126.8 516.6 123.6 530.9 134z"/></svg></div>

    
    <div class="px-3 py-3 font-medium border-b  border-gray-200 ">SOC2 Type II</div>
    <div class="px-3 py-3 border-b  border-gray-200 "><svg style="fill:var(--new_green_accent); height: 1rem; width:1rem;" xmlns="http://www.w3.org/2000/svg" viewBox="0 0 640 640"><path d="M530.8 134.1C545.1 144.5 548.3 164.5 537.9 178.8L281.9 530.8C276.4 538.4 267.9 543.1 258.5 543.9C249.1 544.7 240 541.2 233.4 534.6L105.4 406.6C92.9 394.1 92.9 373.8 105.4 361.3C117.9 348.8 138.2 348.8 150.7 361.3L252.2 462.8L486.2 141.1C496.6 126.8 516.6 123.6 530.9 134z"/></svg></div>
    <div class="px-3 py-3 border-b border-gray-200 "><svg style="fill:var(--new_green_accent); height: 1rem; width:1rem;" xmlns="http://www.w3.org/2000/svg" viewBox="0 0 640 640"><path d="M530.8 134.1C545.1 144.5 548.3 164.5 537.9 178.8L281.9 530.8C276.4 538.4 267.9 543.1 258.5 543.9C249.1 544.7 240 541.2 233.4 534.6L105.4 406.6C92.9 394.1 92.9 373.8 105.4 361.3C117.9 348.8 138.2 348.8 150.7 361.3L252.2 462.8L486.2 141.1C496.6 126.8 516.6 123.6 530.9 134z"/></svg></div>

    
    <div class="px-3 py-3 font-medium border-b  border-gray-200 ">On-Premise deployments</div>
    <div class="px-3 py-3 border-b  border-gray-200 "><svg style="fill:var(--new_green_accent); height: 1rem; width:1rem;" xmlns="http://www.w3.org/2000/svg" viewBox="0 0 640 640"><path d="M530.8 134.1C545.1 144.5 548.3 164.5 537.9 178.8L281.9 530.8C276.4 538.4 267.9 543.1 258.5 543.9C249.1 544.7 240 541.2 233.4 534.6L105.4 406.6C92.9 394.1 92.9 373.8 105.4 361.3C117.9 348.8 138.2 348.8 150.7 361.3L252.2 462.8L486.2 141.1C496.6 126.8 516.6 123.6 530.9 134z"/></svg></div>
    <div class="px-3 py-3 border-b border-gray-200 "><svg style="fill:var(--new_green_accent); height: 1rem; width:1rem;" xmlns="http://www.w3.org/2000/svg" viewBox="0 0 640 640"><path d="M530.8 134.1C545.1 144.5 548.3 164.5 537.9 178.8L281.9 530.8C276.4 538.4 267.9 543.1 258.5 543.9C249.1 544.7 240 541.2 233.4 534.6L105.4 406.6C92.9 394.1 92.9 373.8 105.4 361.3C117.9 348.8 138.2 348.8 150.7 361.3L252.2 462.8L486.2 141.1C496.6 126.8 516.6 123.6 530.9 134z"/></svg></div>

    
    <div class="px-3 py-3 font-medium border-b  border-gray-200 ">Open-source training<br/>& modeling code</div>
    <div class="px-3 py-3 border-b  border-gray-200 "><svg style="fill:var(--new_green_accent); height: 1rem; width:1rem;" xmlns="http://www.w3.org/2000/svg" viewBox="0 0 640 640"><path d="M530.8 134.1C545.1 144.5 548.3 164.5 537.9 178.8L281.9 530.8C276.4 538.4 267.9 543.1 258.5 543.9C249.1 544.7 240 541.2 233.4 534.6L105.4 406.6C92.9 394.1 92.9 373.8 105.4 361.3C117.9 348.8 138.2 348.8 150.7 361.3L252.2 462.8L486.2 141.1C496.6 126.8 516.6 123.6 530.9 134z"/></svg></div>
    <div class="px-3 py-3 border-b border-gray-200 "><svg style="fill:var(--new_green_accent); height: 1rem; width:1rem;" xmlns="http://www.w3.org/2000/svg" viewBox="0 0 640 640"><path d="M530.8 134.1C545.1 144.5 548.3 164.5 537.9 178.8L281.9 530.8C276.4 538.4 267.9 543.1 258.5 543.9C249.1 544.7 240 541.2 233.4 534.6L105.4 406.6C92.9 394.1 92.9 373.8 105.4 361.3C117.9 348.8 138.2 348.8 150.7 361.3L252.2 462.8L486.2 141.1C496.6 126.8 516.6 123.6 530.9 134z"/></svg></div>

    
    <div class="px-3 py-3 font-medium border-b  border-gray-200 ">Free zero-shot voice cloning</div>
    <div class="px-3 py-3 border-b  border-gray-200 ">
    <span class="inline-flex text-xs ">Experimental</span>
    </div>
    <div class="px-3 py-3 border-b border-gray-200 ">
    <span class="inline-flex text-xs ">Experimental</span>
    </div>

    
    <div class="px-3 py-3 font-medium border-b  border-gray-200 ">Audio markups <br/>(emotion/style/non-verbals)</div>
    <div class="px-3 py-3 border-b  border-gray-200 ">
      <span class="inline-flex text-xs ">Experimental</span>
    </div>
    <div class="px-3 py-3 border-b border-gray-200 ">
      <span class="inline-flex  text-xs ">Experimental</span>
    </div>

    
    <div class="px-3 py-3 font-medium  border-gray-200 ">Cross-lingual <br/>(same voice, language switch)</div>
    <div class="px-3 py-3  border-gray-200 ">
    <span class="inline-flex  text-xs ">Experimental</span>
    </div>
    <div class="px-3 py-3">
    <span class="inline-flex  text-xs ">Experimental</span>
    </div>
  </div>
</div>

Explore our latest research advancing the state of the art in speech synthesis, voice cloning, and real-time TTS.

We’ve open-sourced the full training framework behind Inworld TTS‑1—everything from codec to SpeechLM fine-tuning—so you can build your own high-quality TTS models faster.

Inworld + LiveKit: Unlocking studio-quality voice AI for real-time experiences at scale

Inworld + NLX: Enabling multi-modal consumer experiences with SOTA voice AI

Inworld meets Pipecat: Raising the bar for realtime voice AI

Inworld + Vapi: Powering the next generation of expressive, real-time voice agents

Join thousands of developers building the future of consumer AI.

State-of-the-art Voice AI at a radically accessible price point. Join thousands of developers building with 50+ voices and simple cloning in 20+ languages at just $5/million characters.

Introducing Inworld TTS