fix: app's ai site text to speech api

[mnasrautinno]

Important

1. Make sure you have read our contribution guidelines
2. Ensure there is an associated issue and you have been assigned to it
3. Use the correct syntax to link this PR: Fixes #<issue number>.

Summary

Fixes #28090
Motivation: This issue caused TTS feature to stop completely in the Ai Site.
Context: The endpoint should respond with raw chunked bytes from the TTS model plugin but response marshalling made it default to specified model.
Solution: Remove response marshalling as this endpoint returns raw data.

Screenshots

Before	After

Checklist

• This change requires a documentation update, included: Dify Document
• I understand that this PR may be closed in case there was no previous discussion or issues. (This doesn't apply to typos!)
• I've added a test for each change that was introduced, and I tried as much as possible to make a single atomic change.
• I've updated the documentation accordingly.
• I ran dev/reformat(backend) and cd web && npx lint-staged(frontend) to appease the lint gods

[gemini-code-assist]

Summary of Changes

Hello @mnasrautinno, I'm Gemini Code Assist¹! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request addresses a critical bug that rendered the Text-to-Speech functionality in the AI Site inoperable. The change focuses on correcting the API endpoint's response handling to properly stream raw audio data, thereby restoring the feature's intended operation and user experience.

Highlights

• Text-to-Speech API Fix: This pull request resolves a critical issue that caused the Text-to-Speech (TTS) feature in the AI Site to completely stop working. The problem stemmed from incorrect response marshalling on the /text-to-audio endpoint, which was attempting to format raw chunked audio data.
• Response Marshalling Removal: The core of the solution involves removing the response marshalling from the /text-to-audio endpoint. This ensures that the endpoint correctly returns raw, chunked bytes directly from the TTS model plugin, allowing the audio to play as intended.

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature	Command	Description
Code Review	/gemini review	Performs a code review for the current pull request in its current state.
Pull Request Summary	/gemini summary	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help	/gemini help	Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Footnotes

1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

[gemini-code-assist]

Code Review

The pull request correctly addresses the issue where the /text-to-audio endpoint was attempting to marshal raw audio stream data as a JSON object. Removing the text_to_audio_response_fields definition and the @marshal_with decorator ensures that the endpoint can properly return chunked audio bytes, aligning with the intended behavior for text-to-speech functionality. This is a crucial fix for the AI site's TTS feature.