dtinth’s bot: “Raw PCM is ~115 MB/hour, so a day would be over 1 GB. But ac…”

Here! Fresh orphan branch v2 is checked out and empty. Where do you want to start: the transcription model, the audio capture side, or the viewer?

Thai Pangsakulyanont @dtinth20hcd02d86

Let's plan out the project first.

dtinth’s bot @dtinth-bot20h90c5807

Sure. I read the 2024 README: sender, server, fast partial ASR + Gemini batch refine, viewer. First question: keep that two-pass idea, or aim for one realtime model good enough on its own?

Thai Pangsakulyanont @dtinth20h13cc327

Basically, I aim for a single real-time model, but the transcript can be later post-processed with LLM if needed. re. model, see: - https://help.aliyun.com/en/model-studio/real-time-speech-recognition-user-guide?spm=a2c4g.11186623.help-menu-2400256.d_1_2_2_0_1.362dc690INtcxw -…

help.aliyun.comReal-time speech recognition - QwenLearn about real-time speech recognition capabilities, streaming audio calls, and ways to improve recognition results.

dtinth’s bot @dtinth-bot20ha755cbb

mattpocock-skills is already installed as a plugin here. For the per-repo setup, my defaults: 1. Issues: GitHub Issues on dtinth/live-speech 2. Triage labels: the default five 3. Docs: single GLOSSARY.md + docs/adr/ 4. Agent file: AGENTS.md (with CLAUDE.md pointing to it) OK, or…

Thai Pangsakulyanont @dtinth20hb767caa

All agree. More re.directions: - Have a simple web interface. Admin can create room. To create room requires a master password from env file. - Then a room has its own password which can be copied out and sent to teammates e.g. to the audio crew for streaming.

dtinth’s bot @dtinth-bot20hc82f92d

Noted: admin creates rooms with a master password from env; each room gets its own shareable password. Writing setup files now. I need GitHub access for labels/issues: please approve claw grant code 3BR664 (expires in 15 min).

dtinth’s bot @dtinth-bot19hefcb8b3

Setup is committed locally on v2 (AGENTS.md, CLAUDE.md, docs/agents/). The claw grant request 3BR664 lapsed before approval, so labels aren't created yet. Want me to request a new code?

Thai Pangsakulyanont @dtinth19h0913af2

Yes, please.

dtinth’s bot @dtinth-bot19ha61f0d7

New claw grant code: PV43GN (15 min).

dtinth’s bot @dtinth-bot19ha2e0f44

Grant approved, thanks. Triage labels are created on GitHub and setup is committed on v2 (not pushed yet). Next: push v2, then turn your directions into a spec issue? I'd grill you on open questions first, e.g. "server-side VAD": our server, or Qwen's server_vad mode?

Thai Pangsakulyanont @dtinth19h2632251

Please push for server-side VAD. At first, I was thinking about doing VAD ourselves, but since you mentioned that they have their own server VAD, we can use that as well, and it will save us on implementation. In the future, we may be supporting multiple transcription models.…

dtinth’s bot @dtinth-bot19h5dc9752

Pushed: https://github.com/dtinth/live-speech/tree/v2 VAD: a provider adapter either does VAD itself or we do it, hidden behind one interface. Next Q: where does it run? One long-lived Node server with SQLite + audio files on disk would be my default.

GitHubGitHub - dtinth/live-speech at v2Real time speech recognition for live event. Contribute to dtinth/live-speech development by creating an account on GitHub.

Thai Pangsakulyanont @dtinth19h562083a

Agree. You can use Bun too. Deployment target would be Dokploy.

dtinth’s bot @dtinth-bot19h153f29a

Bun it is: bun:sqlite, Bun.serve WebSockets, a Dockerfile with one data volume for Dokploy. Next: frontend. Default is React via Bun's HTML imports, served by the same process (no separate build server). OK?

Thai Pangsakulyanont @dtinth18hf15db2d

Ok as long as we can deploy new server version robustly. Existing connection can cut, but can recover with no data loss. I also have a Sockudo instance, maybe viewers can get notified of changes through it instead? What do you think?

dtinth’s bot @dtinth-bot18h5cd6b78

Good idea. Viewers stay connected while our server redeploys, and fan-out is off our process. Plan: viewer loads a snapshot over HTTP, then applies Sockudo events carrying a sequence number; on a gap or reconnect it refetches. Sender still talks WS to us directly. Sound right?

Thai Pangsakulyanont @dtinth18ha534d11

Sounds right.

dtinth’s bot @dtinth-bot18h4bd8811

Next: should the sender's local buffer survive a tab reload or browser crash? Default: write chunks to IndexedDB, so a reopened sender page resumes uploading what the server hasn't acked, and old acked chunks get pruned.

Thai Pangsakulyanont @dtinth18h33c7010

Yes, but it is possible that we will be streaming for the whole day. So just make sure we don't run into problems with the storage space on the browser

dtinth’s bot @dtinth-bot18h1/2

Raw PCM is ~115 MB/hour, so a day would be over 1 GB. But acked chunks are deleted right away, so the browser only holds the unsent backlog. The sender shows the backlog size and warns as it nears the browser's quota.

09:13 · Nov 13, 2026commit a074e65

dtinth’s bot @dtinth-bot18h2/200e6292

Next: the transcript. Default: a list of segments, each tied to an audio time range, so any segment can be re-transcribed or LLM-cleaned later and replayed as audio. Should admins also be able to hand-edit text live?

Commit