Archive position — measured, not model output
0 likes on Devpost
2,264 of the 7,856 archived projects have more likes, and 5,592 share exactly 0 — so this project's #6,892 place in the like-ranked listing is a tie-break inside that group, not a ranking.
Projects (log scale)
Likes on Devpost. ▲ marks this project's group.
Show the figures
| Likes | Projects | Share of archive |
|---|---|---|
| 0 | 5,592 | 71.2% |
| 1 | 1,758 | 22.4% |
| 2 | 285 | 3.6% |
| 3–4 | 132 | 1.7% |
| 5–9 | 75 | 1.0% |
| 10+ | 14 | 0.2% |
Executive Summary
What the company appears to be
Speakwise is a self-reported tool that claims to offer communication coaching for conversations, based on recorded audio. The author states it uses AI to transcribe conversations, identify communication patterns, and provide evidence-based feedback with rephrased suggestions.
What changed
The project was submitted as part of the OpenAI 2026 hackathon. It is described as a prototype built in a short timeframe using GPT-5.6, AssemblyAI, and Express.js.
The single most important open question
Is there any evidence of real-world usage or customer feedback beyond the author's personal experience?
What The Product Actually Is
The description states that Speakwise is a TypeScript and Express web app built with Codex using GPT-5.6 Terra. It uses AssemblyAI for diarized transcription and GPT-5.6 through the OpenAI Responses API to generate schema-constrained coaching reports.
It turns authorized conversation recordings into speaker-labelled, timestamped transcripts and provides concise coaching reviews that identify evidence-supported communication patterns. Each observation is linked to an exact quote and time, with one strained moment highlighted by a respectful, goal-preserving rephrase.
The app includes an authorization gate, a synthetic demo for testing, deletion controls, sanitization, and a local daily cap for live provider runs.
Evidence The author's own write-up.
Confidence Low — this is self-reported functionality without independent verification or demonstration of actual use.
Positioning & Claim Evolution
The author states that the inspiration came from personal family arguments where it was hard to review constructively. The product aims to offer a private, practical way to revisit actual words said without turning it into a diagnosis or guess about intent.
It positions itself as an evidence-grounded communication coaching tool for conversations.
Evidence The author's own write-up.
Confidence Low — this is a personal claim and not validated by any external data or customer feedback.
Target Customer & ICP
The description does not explicitly state who the target customers are. However, it implies that the product is aimed at individuals who have tense conversations and want to reflect on them constructively, particularly in family settings.
Evidence The author's own write-up.
Confidence Low — no explicit customer segmentation or ICP defined beyond personal use case.
Business Model & Pricing Evidence
There is no evidence of a business model or pricing structure in the description. The project appears to be a prototype submitted for a hackathon, with no indication of monetization plans or pricing tiers.
Evidence Not evidenced.
Confidence Very low — no mention of revenue, pricing, or monetization strategy.
Technical & Delivery Signals
The product is built using:
- TypeScript
- Express.js
- Node.js
- AssemblyAI (for diarized transcription)
- OpenAI GPT-5.6 via the OpenAI Responses API
- Codex for code generation
It includes features such as:
- Authorization gate
- Synthetic demo
- Deletion controls
- Sanitization
- Local daily cap for live provider runs
Evidence The author's own write-up.
Confidence Low — this is a prototype built in a short timeframe, not a production-ready product.
Traction & Maturity Signals
There is no evidence of traction or maturity beyond the project being submitted to a hackathon. No customer data, usage metrics, or adoption indicators are provided.
Evidence Not evidenced.
Confidence Very low — no signs of real-world usage or user engagement.
Competitive Context
The description does not provide any information about competitors or market positioning. It is unclear whether there are existing tools in the communication coaching space that this product might compete with.
Evidence Not evidenced.
Confidence Very low — no competitive analysis or market context provided.
Key Risks & Red Flags
- Unverified claims: All features and functionality are self-reported without independent validation.
- No traction or customers: No evidence of real-world usage or adoption.
- Prototype nature: Built for a hackathon, not intended for production use.
- Privacy concerns: Involves recording and analyzing personal conversations — potential legal and ethical issues.
- Limited scope: Only described for family arguments; unclear if it scales to other domains.
Evidence Not evidenced.
Confidence Moderate — based on the lack of evidence and the prototype nature of the project.
Diligence Questions To Ask The Founders
- What is the actual user base or feedback you've received beyond personal use?
- How do you plan to scale this beyond a hackathon prototype?
- Have you considered privacy, consent, and legal implications of analyzing personal conversations?
- Is there any intention to monetize this product, and if so, how?
- What are the technical limitations or edge cases in processing real-world conversation recordings?
Evidence Not evidenced.
Confidence Low — these questions are based on the lack of information provided.
Investment/Partnership Verdict
There is no evidence to support any commercial viability, traction, or scalability of Speakwise. The project appears to be a hackathon prototype with no demonstrated market need, revenue model, or customer feedback.
Evidence Not evidenced.
Confidence Very low — the description provides no basis for investment or partnership consideration.
Source
Submitted to the OpenAI 2026 hackathon on Devpost. Project home on DevPost.
The analysis above was generated by a language model from the project's own one-line description. It is not independent research and contains no verified traction, revenue or customer data.