VoiceDrop Developers
VoiceDrop's backend is a set of open HTTP APIs running on Cloudflare — your recordings, articles, photos, and writing style are all readable and writable with a single credential. Here's where to start.
Docs
Using wjs-voicedrop
Read and write your VoiceDrop articles / recordings / photos / writing style, trigger mining, and check credits — all with a single sentence in your terminal. Built-in 6+4 phone pairing login, no token copy-pasting.
API Reference
The complete API surface across three services: auth, file / article CRUD, sharing, WeChat Official Account, community, mining triggers, live status, and credit billing. Read this when building your own client.
Three services
| Service | Base URL | Purpose |
|---|---|---|
| Files API | jianshuo.dev/files/api/ | Accounts, recording / article files, photos, sharing, WeChat Official Account, community. The vast majority of calls go here. |
| Agent Worker | jianshuo.dev/agent/ | Mining triggers, live status push (WS), voice-driven edits, credit balance, 6+4 device pairing. |
| Reco Worker | jianshuo.dev/reco/ | Community feed ranking + engagement reporting. Can be unplugged anytime — if it goes down, the main flow is unaffected. |
The data flow in one sentence: upload an .m4a → server-side mining (ASR + Claude) writes out articles/<stem>.json → clients read articles, share, publish to WeChat / the community.