With our API you are able to synthesize speech and transform speech into text.

We support multiple voice/speech models. You can find the complete list along with API reference links at the end of the page.

{% content-ref url="speech-to-text/" %} speech-to-text {% endcontent-ref %}

{% content-ref url="text-to-speech/" %} text-to-speech {% endcontent-ref %}

{% content-ref url="voice-chat/" %} voice-chat {% endcontent-ref %}