Jump to content

Grants:Programs/Wikimedia Community Fund/Rapid Fund/Wikicasts (ID: 23508511)

From Meta, a Wikimedia project coordination wiki
statusDraft
Wikicasts
request or grant IDR-RF-2507-19604
proposed start date2025-10-01
proposed end date2026-01-01
requested budget (local currency) 
requested budget (USD) USD
grant typeIndividual
funding regionunknown region
decision fiscal year2025-26
applicantpeteabu
organization (if applicable)N/A

Applicant details

[edit]
Main Wikimedia username. (required)

peteabu

Organization

N/A

If you are a group or organization leader, board member, president, executive director, or staff member at any Wikimedia group, affiliate, or Wikimedia Foundation, you are required to self-identify and present all roles. (required)

N/A

Describe all relevant roles with the name of the group or organization and description of the role. (required)

Main proposal

[edit]
1. State the title of your proposal. This will also be the Meta-Wiki page title.

Wikicasts

2. and 3. Proposed start and end dates for the proposal.

2025-10-01 - 2026-01-01

4. What is your tech project about, and how do you plan to build the product?

Include the following points in your answer:

  • Project goal and problem you solve
  • Product strategy or project roadmap
  • Technical approach (infrastructure, tech stack, key tools and services)
  • Integrations or dependencies (if any)
Project Goal and Problem Solved
[edit]

WikiCasts makes Wikipedia content more accessible and engaging by converting articles into two-person conversational audio formats using AI. While Wikipedia is rich in content, it can be dense and intimidating for casual users, auditory learners, or those with visual or cognitive impairments. This project reimagines article consumption by turning static text into natural, dialogue-driven podcasts; making knowledge feel like a conversation between curious minds.

While TTS tools exist, they typically read articles as monotone monologues. WikiCasts reimagines articles as natural-sounding, back-and-forth conversations that are easier to follow, retain, and enjoy, all while preserving attribution and linking back to the original article.

Product Strategy and Roadmap
[edit]
The product is already in working MVP form (usewikicasts.com). With this grant, I aim to:
[edit]
  • Improve the quality and clarity of the generated conversations
  • Hire a supporting developer to help with maintenance
  • Expand support for multilingual content (starting with 1–2 additional languages)
  • Migrate the product off Replit, where it is currently hosted, to a more affordable platform.
Technical Approach
[edit]
  • Platform: Replit (development and production deployment)
  • Environment: Node.js runtime with TypeScript compilation

Backend Tech Stack

  • Runtime: Node.js with Express.js framework
  • Language: TypeScript for type safety
  • Database: PostgreSQL via Neon Database (serverless)
  • ORM: Drizzle ORM with type-safe queries
  • Authentication: Session-based auth with Passport.js (Google OAuth, this is entirely optional and not required for usage)
  • WebSockets: Native WebSocket server for real-time audio analysis

Frontend Tech Stack

  • Framework: React 18 with TypeScript
  • Routing: Wouter (lightweight client-side routing)
  • Styling: Tailwind CSS with Radix UI components
  • State Management: TanStack Query for server state
  • Build Tool: Vite for development and production builds
  • Audio: Native HTML5 Audio API with WebSocket integration

AI & Content Generation Services

  • Language Models:
    • OpenAI (GPT-4, GPT-4o, GPT-4 Turbo)
    • Google Gemini (1.5 Pro, 1.5 Flash)
    • Deepseek (Reasoner, Chat R1)
  • Text-to-Speech: Google Cloud TTS (Chirp) as primary provider
  • Content Source: Wikipedia API for article fetching

Key Architecture Features

  • Multi-stage Processing: Content planning → Generation → Audio synthesis → File storage
  • Dual Storage: Database for metadata, filesystem for audio files
  • Real-time Updates: WebSocket connections for processing status
  • Context Compression: Advanced AI context management for multi-chunk generation
  • Chapter Normalization: Dynamic timestamp adjustment based on actual audio duration
  • Coherence Enhancement: Final pass to improve transcript quality
5. What is the expected impact of your project, and how will you measure success?

Include the following points in your answer:

  • Milestones and progress tracking
  • Project impact and success metrics

Expected Impact and Success Metrics

Project Impact:WikiCasts aims to expand Wikipedia’s reach and inclusivity by converting articles into engaging, conversational audio content. This specifically benefits auditory learners, visually impaired users, multilingual audiences, and casual readers who prefer conversational formats to traditional text-based articles.

Milestones & Progress Tracking:Progress will be transparently tracked via GitHub issues, clearly aligned to our strategic roadmap:

  • Month 1 (Quality Enhancement & Infrastructure Migration):
    • Improve the naturalness and clarity of AI-generated dialogues.
    • Migrate the application infrastructure from Replit to a more affordable, scalable hosting platform (e.g., DigitalOcean or Render).
  • Month 2 (Developer Onboarding & Multilingual Support):
    • Hire and onboard a supporting developer for ongoing maintenance, bug fixes, and feature enhancements.
    • Implement multilingual support, initially targeting one additional language (e.g., French or Hausa)

Success Metrics:

  • Content Generation: Successfully publish 50+ conversational WikiCasts by the end of month 3.
  • Audience Reach: Attract at least 500 listens/views on generated WikiCasts.
  • Technical Stability: Achieve stable performance post-migration from Replit, with clear documentation on cost reduction and scalability improvements.
  • Community Engagement: Positive qualitative feedback from at least 50 users, educators, or Wikimedia community members 
  • Multilingual Accessibility: Demonstrable engagement with newly supported multilingual content, showing uptake by diverse language communities.

Metrics will be monitored using web analytics, direct user feedback, and GitHub activity, ensuring accountability, transparency, and measurable impact.

6. Who is your target audience, and how have you confirmed there is demand for this project? How did you engage with the Wikimedia community?

Include the following points in your answer:

  • Project demand and target audience description
  • Links to interaction(s) with Wikimedia community
  • Evidence from community consultation such as the [Community Wishlist]


7. How will your team predict and manage potential user security and privacy risks, and what risks do you currently see?

Include the following points in your answer:

  • The level of in-house or consulted security and privacy expertise you will have available to you during delivery of this project
  • How your development, testing, and deployment processes mitigate the introduction of unnecessary security or privacy risks


8. Who is on your team, and what is your experience?

Include the following points in your answer:

  • Your experience as a developer, relevant past projects
  • Wikimedia SUL (developer), Gerrit, Github, Gitlab or other relevant public account handles
  • Other team members, their roles and expertise


9. How will the project be maintained long-term?

Include the long-term maintenance plan with maintainer(s) in your answer. If you expect the long-term maintenance to incur expenses, please list those and the plan for long-term expense coverage.


10. Under what license will your code be released, and how will you ensure the product is well documented?

Include the following points in your answer:

  • Code license and compatibility with Wikimedia projects
  • Documentation plan


11. Will your project depend on or contribute to third-party tools or services?


12. Is there anything else you’d like to share about your project? (optional)


Budget

[edit]
13. Upload your budget for this proposal or indicate the link to it. (required)


14. and 15. What is the amount you are requesting for this proposal? Please provide the amount in your local currency. (required)


16. Convert the amount requested into USD using the Oanda converter. This is done only to help you assess the USD equivalent of the requested amount. Your request should be between 500 - 5,000 USD.

 USD

We/I have read the Application Privacy Statement, WMF Friendly Space Policy and Universal Code of Conduct.

No

Endorsements and Feedback

[edit]

Please add endorsements and feedback to the grant discussion page only. Endorsements added here will be removed automatically.

Community members are invited to share meaningful feedback on the proposal and include reasons why they endorse the proposal. Consider the following:

  • Stating why the proposal is important for the communities involved and why they think the strategies chosen will achieve the results that are expected.
  • Highlighting any aspects they think are particularly well developed: for instance, the strategies and activities proposed, the levels of community engagement, outreach to underrepresented groups, addressing knowledge gaps, partnerships, the overall budget and learning and evaluation section of the proposal, etc.
  • Highlighting if the proposal focuses on any interesting research, learning or innovation, etc. Also if it builds on learning from past proposals developed by the individual or organization, or other Wikimedia communities.
  • Analyzing if the proposal is going to contribute in any way to important developments around specific Wikimedia projects or Movement Strategy.
  • Analysing if the proposal is coherent in terms of the objectives, strategies, budget, and expected results (metrics).

Endorse


This is an automatically generated Meta-Wiki page. The page was copied from Fluxx, the web service of Wikimedia Foundation Funds, where the user has submitted their application. Please do not make any changes to this page because all changes will be removed after the next update. Use the discussion page for your feedback. The page was created by CR-FluxxBot.