# Using inference api on model that returns an audio file

**URL:** <https://discuss.huggingface.co/t/using-inference-api-on-model-that-returns-an-audio-file/12190>\
**Category:** Models\
**Created:** [November 23, 2021, 9:43am UTC](https://discuss.huggingface.co/t/using-inference-api-on-model-that-returns-an-audio-file/12190 "2021-11-23T09:43:38Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![danijelpetkovic](https://avatars.discourse-cdn.com/v4/letter/d/e8c25b/32.png) [@danijelpetkovic](https://discuss.huggingface.co/u/danijelpetkovic)\
**Post date:** [November 23, 2021, 9:43am UTC](https://discuss.huggingface.co/t/using-inference-api-on-model-that-returns-an-audio-file/12190/1 "2021-11-23T09:43:39Z")

</div>

Hello! How can I use the inference api on a model that receives text and returns audio file. I am trying to use this model: espnet/kan-bayashi\_ljspeech\_vits. What should response look like from the inference api? Thanks:)