# Fine tuning a TTS model

**URL:** <https://discuss.huggingface.co/t/fine-tuning-a-tts-model/33218>\
**Category:** Models\
**Created:** [March 7, 2023, 7:16am UTC](https://discuss.huggingface.co/t/fine-tuning-a-tts-model/33218 "2023-03-07T07:16:29Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![anjalyjayakrishnan](https://avatars.discourse-cdn.com/v4/letter/a/b782af/32.png) [@anjalyjayakrishnan](https://discuss.huggingface.co/u/anjalyjayakrishnan)\
**Post date:** [March 7, 2023, 7:16am UTC](https://discuss.huggingface.co/t/fine-tuning-a-tts-model/33218/1 "2023-03-07T07:16:29Z")

</div>

Hello,

Went through HF documentation about Text-To-Speech here : [What is Text-to-Speech? - Hugging Face](https://huggingface.co/tasks/text-to-speech#:~:text=TTS%20models%20are%20used%20to,natural%20speech%20such%20as%20emphasis). Does hugging face provides any functionality to fine-tune a TTS model?

Looking forward for the reply.