feat: Add Japanese language support for podcast generation #11
Conversation
- Add Japanese prompts for natural conversation between host (花子) and guest (太郎) - Implement Azure TTS with Japanese voices (ja-JP-NanamiNeural, ja-JP-KeitaNeural) - Add language selection UI with globe icon in CustomizationDropdown - Update API endpoints to accept language parameter - Create Select component for language selection - Support both English and Japanese podcast generation 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <[email protected]>
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
There was a problem hiding this comment.
Summary of Changes
Hello @MASAKASUNO1, 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 significantly enhances the GitPodcast application by introducing full Japanese language support. It allows users to generate podcasts in Japanese with localized prompts and voices, achieved through updates to both the frontend user interface for language selection and the backend logic for dynamic content and SSML generation.
Highlights
- Japanese Language Support: Implemented comprehensive Japanese language support for podcast generation, including Japanese prompts and natural-sounding Japanese TTS voices (Hanako and Taro).
- Dynamic Prompt and SSML Generation: The backend now dynamically selects between English and Japanese prompts for content generation and sets the appropriate
xml:langattribute (ja-JPoren-US) in the SSML for correct text-to-speech rendering. - Language Selection UI: A new language selection dropdown, represented by a globe icon, has been added to the frontend's
CustomizationDropdowncomponent, allowing users to easily switch between English and Japanese. - API Language Parameter: All relevant backend API endpoints (
/generate,/generate_slide) and frontend API calls (generateAndCacheDiagram,generateSlide,generateAudio) now accept and utilize alanguageparameter to control the generated content and audio. - Frontend State Management: The
useDiagramhook now manages the selected language state, ensuring that language preferences are propagated throughout the application for content generation.
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 in your pull request via creating an issue comment (i.e. comment on the pull request page) using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands.
| 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 issue 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 or fill out our survey to provide feedback.
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
-
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. ↩
There was a problem hiding this comment.
Code Review
This pull request introduces Japanese language support for podcast generation, with changes in both the Python backend and the TypeScript/React frontend. The review suggests refactoring repeated language-based conditional logic, using typing.Literal for stricter API input validation, avoiding unsafe prop fallbacks, and moving hardcoded values to constants for improved maintainability and robustness.
| api_key: str | None = None | ||
| audio: bool = False # new param | ||
| audio_length: str = 'long' | ||
| language: str = 'en' # new param for language selection |
There was a problem hiding this comment.
Consider using typing.Literal to restrict the language field to supported values ('en', 'ja') for improved data validation. This should also be applied to the SlideRequest model on line 207.
| language: str = 'en' # new param for language selection | |
| language: Literal['en', 'ja'] = 'en' # new param for language selection |
| prompt = PODCAST_SSML_PROMPT_JP if language == 'ja' else PODCAST_SSML_PROMPT | ||
| ssml_response = process_github_content(combined_content, prompt, 250000, 100000) |
There was a problem hiding this comment.
The prompt selection logic is duplicated. Consider centralizing the prompt configuration to avoid repetition and improve maintainability. This applies to lines 151, 183, and 292 as well.
| <SelectItem value="en">English</SelectItem> | ||
| <SelectItem value="ja">日本語</SelectItem> |
There was a problem hiding this comment.
The language options in the dropdown are hardcoded. Define these options as a constant array of objects for better maintainability.
| language={language || "en"} | ||
| onLanguageChange={onLanguageChange || (() => {})} |
There was a problem hiding this comment.
The || operator provides default fallbacks for props that are required by the child CustomizationDropdown component. It's safer to pass the props directly and make the language and onLanguageChange props non-optional in MainCardProps if they are always expected when showCustomization is true.
language={language}
onLanguageChange={onLanguageChange}1 participant
Summary
This PR adds comprehensive Japanese language support to GitPodcast, enabling users to generate podcasts in Japanese with natural conversation between Japanese hosts.
🌍 Features Added
🔧 Technical Changes
Backend:
prompts_jp.pywith Japanese conversation promptslanguageparameterFrontend:
useDiagramhook🎭 User Experience
Users can now:
🧪 Test Plan
This enhancement makes GitPodcast accessible to Japanese-speaking developers and expands the global reach of the project.
🤖 Generated with Claude Code