Amuse and Spark – Running Live Talking AI Avatars on an ESP32
← Blog Release Introducing Amuse and Spark Two open-source apps you can talk to, running on a few-dollar ESP32-S3 watch board. Spark is a voice agent that connects straight to OpenAI's Realtime API. Amuse puts five animated video characters on the screen.
- ▪← Blog Release Introducing Amuse and Spark Two open-source apps you can talk to, running on a few-dollar ESP32-S3 watch board.
- ▪Spark is a voice agent that connects straight to OpenAI's Realtime API.
- ▪Amuse puts five animated video characters on the screen.
Hacker News (AI / LLM) files mainly under ai. We currently carry 7,439 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | GEA |
| Canonical URL | https://geastack.com/blog-introducing-amuse-and-spark |
| Publication time | Sat, 03 Oct 2026 14:58:02 +0000 |
| Retrieval time | 2026-10-03T15:08:17.949Z |
| Last seen | 2026-10-03T15:08:17.949Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | DTZNZ1FH-4_4 · 1 stories |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
← Blog Release Introducing Amuse and Spark Two open-source apps you can talk to, running on a few-dollar ESP32-S3 watch board. Spark is a voice agent that connects straight to OpenAI's Realtime API. Amuse puts five animated video characters on the screen. Both are written in TypeScript, JSX and CSS and compiled to native firmware with GeaStack. Armağan Amcalar · Oct 3, 2026 · 4 min read Both apps run on the Waveshare ESP32-S3 Touch AMOLED 2.06, the watch-shaped board from our first post, and Amuse also runs on its 1.8″ sibling. You swipe to pick a character, tap Start, and talk. The source for both is on GitHub: geastack.com/amuse geastack.com/spark Spark Spark: swipe between KITT, Nova, Echo and Flora, tap Start, and talk. Spark is a voice agent.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at GEA.
Discussion
0 commentsMore from GEA
