talkPoetry

The company appears to be a solo-developer project named talkPoetry, a voice-based creativity app for adults to discuss poetry with AI. The author states it was built as part of the OpenAI 2026 hackathon and is intended for use in retirement homes, where retirees may recall poetry from their youth but not recent memories. The app uses GPT-4o-mini-tts for transcription and GPT-5.6-Luna for responses, with a simple interface and AI voice that changes every two dialogues to avoid personal connection.

What changed: This is a self-reported prototype or hackathon submission, not a product in market. There is no evidence of revenue, customers, or adoption beyond the author's own account.

The single most important open question: Is there any evidence of user testing, feedback loops, or traction that would indicate whether this concept has commercial viability or appeal beyond the author’s personal vision?

• The description states: talkPoetry is a voice-based app for adults to discuss poetry with AI.
• It is described as a webapp built with Node.js, using GPT-4o-mini-tts for transcription and GPT-5.6-Luna for responses.
• The app has a simple interface, and non-poetry-related information is filtered out to avoid personalization.
• AI voice changes every two dialogue turns, per the author’s stated intent.

Note: No evidence of actual product functionality or user experience beyond the author's own description.

• The author states: "I have had this idea since middle school."
• The app is positioned for retirement homes, where retirees may recall poetry from their youth.
• It also aims to combat loneliness in adults.
• The author mentions that the app can be used like a device similar to Alexa, but with a focus on poetry.

Inference: The positioning seems to be rooted in nostalgia and emotional connection rather than commercial scalability. No evidence of market research or user feedback to support this positioning.

• The author states: "It can be useful in retirement homes."
• The target audience is described as adults, particularly those who may be lonely or have a connection to poetry from their youth.
• No further segmentation or definition of the specific customer profile beyond this.

Not evidenced: No evidence of defined ICP, user personas, or market research. The description does not indicate whether the app targets individuals, institutions, or caregivers.

• The author states: "It is a voice based app with a very simple interface."
• There is no mention of pricing, monetization, or business model.
• No evidence of revenue streams, subscription plans, or paid features.

Not evidenced: No indication of how the product would generate revenue or whether it is intended to be free, freemium, or paid.

• The app was built using:
  • GPT-4o-mini-tts for transcription
  • GPT-5.6-Luna for responses
  • Node.js
  • Poetry (as a framework or language)
  • Voice (as a feature)
  • Webapp (as delivery method)

Inference: The use of AI models suggests an experimental or prototype nature, not a production-ready solution. No evidence of scalability, infrastructure, or deployment details.

• The project is described as a hackathon submission.
• The author states: "I used codex and gpt-5.6-luna for responses."
• Accomplishments include: "made a simple decent app".
• The next step is to "make it realtime and show it to others".

Not evidenced: No evidence of user adoption, feedback, or product iteration beyond the initial prototype. No data on usage, retention, or engagement.

• No mention of competitors in the description.
• No indication of market analysis or competitive positioning.
• The author does not reference similar products or services in the space of voice-based poetry or AI companions for loneliness.

Not evidenced: No evidence of competitive landscape or differentiation strategy.

• The project is a single-person hackathon submission, with no team, funding, or commercial traction.
• The app is described as "simple" and "decent", not scalable or polished.
• The AI voice changing every two turns may be a design choice to avoid emotional connection, but it could also reduce user engagement.
• No evidence of user testing, feedback, or iteration beyond the author’s own account.

Inference: The risk is high that this remains an unproven concept with no clear path to market traction or monetization.

1. What specific user feedback have you received on the prototype?
2. Have you tested the app with actual users in retirement homes or other target environments?
3. What is your plan for scaling beyond a hackathon submission?
4. How do you intend to monetize this product, if at all?
5. Are there any existing partnerships or institutional interest in deploying this in real-world settings?