# Undefined error on Inference API (serverless) for several HF text-to-speech tasks **URL:** \ **Category:** Beginners\ **Created:** [March 29, 2024, 2:33am UTC](https://discuss.huggingface.co/t/undefined-error-on-inference-api-serverless-for-several-hf-text-to-speech-tasks/79230 "2024-03-29T02:33:48Z")\ **Posts on this page:** 6\ **Page:** 1
**Author:** ![Bagus](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/bagus/32/27606_2.png) [@Bagus](https://discuss.huggingface.co/u/Bagus)\ **Post date:** [March 29, 2024, 2:33am UTC](https://discuss.huggingface.co/t/undefined-error-on-inference-api-serverless-for-several-hf-text-to-speech-tasks/79230/1 "2024-03-29T02:33:48Z")
I tried several TTS models on the HF web (by typing my text below “Inference API” on the right side of the HF page). Here are several examples, including my own: - [microsoft/speecht5\_tts · Hugging Face](https://huggingface.co/microsoft/speecht5_tts) - [reach-vb/XTTS-v2 · Hugging Face](https://huggingface.co/reach-vb/XTTS-v2) - [Bagus/speecht5\_finetuned\_voxpopuli\_nl · Hugging Face](https://huggingface.co/Bagus/speecht5_finetuned_voxpopuli_nl) - [Bagus/speecht5\_finetuned\_commonvoice\_id · Hugging Face](https://huggingface.co/Bagus/speecht5_finetuned_commonvoice_id) All error messages are the same: Undefined (see attached). Does anyone know how to solve this issue? ![image](https://us1.discourse-cdn.com/hellohellohello/original/3X/b/e/be8216d5ec703605e3dc68ae2b598f9febeedbda.png) ---
**Author:** ![0018akhil](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/0018akhil/32/25796_2.png) [@0018akhil](https://discuss.huggingface.co/u/0018akhil)\ **Post date:** [April 13, 2024, 2:32pm UTC](https://discuss.huggingface.co/t/undefined-error-on-inference-api-serverless-for-several-hf-text-to-speech-tasks/79230/2 "2024-04-13T14:32:45Z")
@Bugus I have checked the call it gives the internal server error. ![image](https://us1.discourse-cdn.com/hellohellohello/original/3X/2/7/27fc6da131c8d6de4d242a379730eb954878a04d.png) ---
**Author:** ![AK-12](https://avatars.discourse-cdn.com/v4/letter/a/3da27b/32.png) [@AK-12](https://discuss.huggingface.co/u/AK-12)\ **Post date:** [July 8, 2024, 5:53pm UTC](https://discuss.huggingface.co/t/undefined-error-on-inference-api-serverless-for-several-hf-text-to-speech-tasks/79230/3 "2024-07-08T17:53:35Z")
I am also encountering an “Internal Server Error” while trying to use the Inference API for both my own fine-tuned Speech T5 model and the original Microsoft Speech T5 model. This issue persists across different environments, including Google Colab and Visual Studio Code. I have opened a discussion on Hugging Face’s forum here: [microsoft/speecht5\_tts · Internal Server Error while using Inference API for Speech T5](https://huggingface.co/microsoft/speecht5_tts/discussions/46) If anyone has experienced similar issues or has a possible solution, please share! ---
**Author:** ![AaravAsawa](https://avatars.discourse-cdn.com/v4/letter/a/58956e/32.png) [@AaravAsawa](https://discuss.huggingface.co/u/AaravAsawa)\ **Post date:** [August 25, 2024, 8:12am UTC](https://discuss.huggingface.co/t/undefined-error-on-inference-api-serverless-for-several-hf-text-to-speech-tasks/79230/4 "2024-08-25T08:12:31Z")
same issue here ---
**Author:** ![deagar](https://avatars.discourse-cdn.com/v4/letter/d/a4c791/32.png) [@deagar](https://discuss.huggingface.co/u/deagar)\ **Post date:** [November 18, 2024, 3:39am UTC](https://discuss.huggingface.co/t/undefined-error-on-inference-api-serverless-for-several-hf-text-to-speech-tasks/79230/5 "2024-11-18T03:39:52Z")
Also experiencing this same issue with every TTS model I’ve tried on the serverless inference API. ---
**Author:** ![John6666](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/john6666/32/27664_2.png) [@John6666](https://discuss.huggingface.co/u/John6666)\ **Post date:** [November 18, 2024, 3:45am UTC](https://discuss.huggingface.co/t/undefined-error-on-inference-api-serverless-for-several-hf-text-to-speech-tasks/79230/6 "2024-11-18T03:45:29Z")
The **Serverless Inference API** is currently turned off for most models. This is probably because the shared resources on the server have been exhausted. It is turned on for **microsoft/speecht5\_tts** , but it does not actually work because the configuration settings are not properly set in **README.md** or json. It is better to load it locally or in Spaces and use it.