deepseek-ai/awesome-deepseek-integration
1
0
Fork 0
mirror of https://github.com/deepseek-ai/awesome-deepseek-integration.git synced 2026-11-05 00:57:30 +00:00
Code Issues 184 Projects Packages Wiki Activity

[PR #762] Add esp32-thinks: ESP32 voice assistant with a DeepSeek brain #737

New issue
Open
opened 2026-10-26 10:01:09 +00:00 by bsakaguchi · 0 comments
bsakaguchi commented 2026-10-26 10:01:09 +00:00
Owner
Copy link

📋 Pull Request Information

Original PR: https://github.com/deepseek-ai/awesome-deepseek-integration/pull/762
Author: @raullenchai
Created: 10/13/2026
Status: 🔄 Open

Base: main ← Head: main

📝 Commits (3)

  • fbcb6df ci: add Manzanita Apple Silicon canary
  • 7366fe6 Add esp32-thinks: ESP32 voice assistant with DeepSeek brain (QuickSilver preset)
  • 7a39f7f Add esp32-thinks logo

📊 Changes

3 files changed (+27 additions, -0 deletions)

View changed files

➕ .github/workflows/manzanita-canary.yml (+23 -0)
📝 README.md (+4 -0)
➕ docs/esp32-thinks/assets/logo.png (+0 -0)

📄 Description

Adds esp32-thinks to Applications (logo at docs/esp32-thinks/assets/logo.png).

What it is: a personal AI voice assistant on an ESP32-S3 — say "Hi, ESP" (esp-sr WakeNet10, on-chip) or press the knob, and it answers out loud with streaming sentence TTS while the model is still writing.

Why it belongs here: the brain is three independent OpenAI-compatible endpoints (STT / chat / TTS) — the quicksilver preset runs deepseek-v4.1-flash as the chat model (with reasoning.exclude to skip its thinking phase for voice latency), whisper-large-v3-turbo for STT and chatterbox/qwen3-tts for speech. Any endpoint can also be pointed at DeepSeek's official API.

Built on Meta's open-source muse-gadget-sdk, verified end-to-end on a Seeed SenseCAP Watcher. MIT.

Happy to adjust the wording or section placement.

🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.

## 📋 Pull Request Information **Original PR:** https://github.com/deepseek-ai/awesome-deepseek-integration/pull/762 **Author:** [@raullenchai](https://github.com/raullenchai) **Created:** 10/13/2026 **Status:** 🔄 Open **Base:** `main` ← **Head:** `main` --- ### 📝 Commits (3) - [`fbcb6df`](https://github.com/deepseek-ai/awesome-deepseek-integration/commit/fbcb6df97ee2714a993ecd12f7563ea8946ad6c2) ci: add Manzanita Apple Silicon canary - [`7366fe6`](https://github.com/deepseek-ai/awesome-deepseek-integration/commit/7366fe6814235e3770d60bc2825f3270a56fdb75) Add esp32-thinks: ESP32 voice assistant with DeepSeek brain (QuickSilver preset) - [`7a39f7f`](https://github.com/deepseek-ai/awesome-deepseek-integration/commit/7a39f7f2e3c02de4a41354c7c46891366d50298c) Add esp32-thinks logo ### 📊 Changes **3 files changed** (+27 additions, -0 deletions) <details> <summary>View changed files</summary> ➕ `.github/workflows/manzanita-canary.yml` (+23 -0) 📝 `README.md` (+4 -0) ➕ `docs/esp32-thinks/assets/logo.png` (+0 -0) </details> ### 📄 Description Adds [esp32-thinks](https://github.com/raulenchai/esp32-thinks) to **Applications** (logo at `docs/esp32-thinks/assets/logo.png`). **What it is:** a personal AI voice assistant on an ESP32-S3 — say "Hi, ESP" (esp-sr WakeNet10, on-chip) or press the knob, and it answers out loud with streaming sentence TTS while the model is still writing. **Why it belongs here:** the brain is three independent OpenAI-compatible endpoints (STT / chat / TTS) — the **quicksilver preset runs `deepseek-v4.1-flash`** as the chat model (with `reasoning.exclude` to skip its thinking phase for voice latency), whisper-large-v3-turbo for STT and chatterbox/qwen3-tts for speech. Any endpoint can also be pointed at DeepSeek's official API. Built on Meta's open-source muse-gadget-sdk, verified end-to-end on a Seeed SenseCAP Watcher. MIT. Happy to adjust the wording or section placement. --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>
Sign in to join this conversation.
No Branch/Tag specified
Branches Tags
main
No results found.
Labels
Clear labels   
pull-request
Mirrored from GitHub Pull Request

No labels
pull-request
Milestone
Clear milestone
No items
No milestone
Projects
Clear projects
No items
No project
Assignees
Clear assignees
No assignees
1 participant
Notifications
Due date
The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Dependencies

No dependencies set.

Reference
deepseek-ai/awesome-deepseek-integration#737
No description provided.