{
 "schema_version": 1,
 "generated": "2026-10-20",
 "id": "raullenchai-esp32-thinks--mix-speech-chat-tts-providers-per-task",
 "repo": "raullenchai/esp32-thinks",
 "repo_url": "https://github.com/raullenchai/esp32-thinks",
 "repo_slug": "raullenchai-esp32-thinks",
 "title": "Route speech, chat and TTS to different AI servers",
 "page_title": "How to route speech, chat and TTS to different AI servers with Esp32 Thinks",
 "summary": "Point each of the three endpoints at a different OpenAI-compatible server using the custom preset.",
 "who": "A developer who wants cheaper transcription, a stronger chat model, or a local server for one task and not the others.",
 "problem": "Most voice products tie all three tasks to one vendor, so you cannot pick the best or cheapest option for each step.",
 "outcome": "Your gadget uses one provider for transcription, another for chat and a third for speech, all set in one config file and a rebuild.",
 "steps": [
  "Clone the SDK at the pinned commit: `git clone https://github.com/facebookincubator/muse-gadget-sdk.git` then `git -C muse-gadget-sdk checkout 812c46f`",
  "Clone and enter this repo: `git clone https://github.com/raullenchai/esp32-thinks.git` then `cd esp32-thinks`",
  "Apply the patch with the custom preset: `./apply.sh ../muse-gadget-sdk --preset custom` (inferred, check the README)",
  "Enter a separate base URL and key for the speech, chat and TTS endpoints when apply asks for them",
  "Build and flash: `./build-and-flash.sh ../muse-gadget-sdk /dev/ttyACM1`"
 ],
 "agent_prompt": "In the esp32-thinks repo, apply the custom preset with separate STT, chat and TTS endpoints for <provider-list>, then confirm the generated provider config lists three different base URLs. Verify by running a typed probe with python3 scripts/tts_probe.py /dev/ttyACM1 \"hello?\" and checking that a reply is produced.",
 "agents": [
  "any"
 ],
 "difficulty": "Advanced",
 "time": "3 hours",
 "basis": "readme",
 "caveat": "The README says each endpoint pins its own root CA and session tickets never cross origins, so mixed providers do not share a TLS session and first replies can be slower.",
 "category": "Personal productivity",
 "tags": [
  "Personal productivity"
 ],
 "lang": "shell",
 "requirements": [
  "A Seeed SenseCAP Watcher W1-B or another board the SDK supports",
  "A Linux or macOS build host with ESP-IDF v6.0.x for esp32s3",
  "Git and USB access to the device serial port",
  "Wi-Fi credentials for the config step",
  "API keys for the chosen provider (OpenAI, QuickSilver, or your own OpenAI-compatible server)",
  "Docker or Node.js and optionally Tailscale for the openmuse agent"
 ],
 "risk": "sensitive",
 "seen_in_the_wild": false,
 "mentioned_publicly": false,
 "risks": [
  {
   "tag": "credentials",
   "notice": "Each endpoint needs its own API key, and every key is stored in the generated device config."
  }
 ],
 "best": false,
 "score": 0.9,
 "evidence": [],
 "url": "https://dedupedai.com/use-cases/raullenchai-esp32-thinks/mix-speech-chat-tts-providers-per-task/",
 "md": "https://dedupedai.com/use-cases/raullenchai-esp32-thinks/mix-speech-chat-tts-providers-per-task/index.md",
 "disclaimer": "Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked \"Seen in the wild\", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email hello@dedupedai.com and we will look at it promptly.",
 "api": "https://dedupedai.com/api/v1/usecases/raullenchai-esp32-thinks--mix-speech-chat-tts-providers-per-task.json",
 "api_version": "v1"
}