textflowkit 0.1.9__tar.gz → 0.1.11__tar.gz

{textflowkit-0.1.9 → textflowkit-0.1.11}/.github/workflows/ci.yml

@@ -90,6 +90,6 @@ jobs:
           python -m pip install "setuptools>=83" "build>=1.2"
           python -m build --wheel
           python -m build --wheel --outdir dist packages/textflowkit-fonts
-      - name: Smoke all three installed entry points
+      - name: Smoke all four installed entry points (CLI, MCP, HTTP, served UI)
         shell: bash
         run: python scripts/smoke_installed_wheel.py dist/textflowkit-*.whl dist/textflowkit_fonts-*.whl

{textflowkit-0.1.9 → textflowkit-0.1.11}/CHANGELOG.md

@@ -1,5 +1,97 @@
 # Changelog
 
+## v0.1.11 — 2026-10-06
+
+Optional native live streaming supports **Windows x86_64 only**. Core version:
+0.1.11; unchanged optional fonts: 0.1.6. Existing standalone Whistle defaults,
+file/URL jobs, CLI, and MCP behavior are unchanged. The public site remains static
+documentation and serves no streams. Local source validation does not establish
+published-package verification or cross-platform live support.
+
+
+### Added
+
+- **Public `StreamingSession` API.** Bounded PCM feed, typed incremental events,
+  flush/finish, cancellation, canonical final `Transcript`, and context-manager
+  cleanup. One owned native child per session binds directly to the separately
+  pinned `libneedle3.dll`; no upstream Python SDK or telemetry module is loaded.
+  Live sessions are ephemeral, with no replay or durable resume.
+- **Live microphone streaming (opt-in, loopback-only).** When
+  `TEXTFLOWKIT_STREAMING=1` is set, the developer HTTP app serves a `/stream`
+  WebSocket and the local UI serves `/api/stream`, both transcribing audio as it
+  arrives. A runnable, self-hosted browser example is at `/streaming-example`
+  (and `/api/streaming-example` under the UI); its `AudioWorklet` resamples any
+  device rate to 16 kHz mono with continuous phase. Off by default: with the
+  switch unset the endpoint does not exist. The standalone `textflowkit` CLI is
+  unaffected — it does not open a microphone or a streaming socket. Requires the
+  new `streaming` extra (`pip install "textflowkit[streaming]"`), which adds the
+  `websockets` dependency. Auth is fail-closed: the UI accepts only its own origin
+  and capability, the standalone API requires the API token (even in developer
+  mode), and a separate origin may stream only if the operator lists it in
+  `TEXTFLOWKIT_STREAMING_ORIGINS` (a browser needs its own origin listed, including
+  the standalone example's). See [docs/streaming.md](docs/streaming.md).
+  **Bounded live runs verified on this machine's native engine** — 65 s and 300 s
+  through the product core on Windows x86_64. A separate assembled UI WebSocket
+  run fed prerecorded PCM at real time for 12 s. Browser lifecycle and resampling
+  checks used fake audio; **physical microphone capture was not verified**. Only
+  English was measured natively; the other six accepted languages and live
+  Linux/macOS were not exercised. No public remote streaming is provided.
+
+## v0.1.10 — 2026-10-06
+
+**The local browser interface ships.** The loopback-only browser workspace
+(`textflowkit-ui`) is now part of the core package rather than source-only, so a
+regular install of this release carries the command. Core version: 0.1.10;
+unchanged optional fonts: 0.1.6.
+
+### Added
+
+- **Local browser interface in the core package.** `textflowkit-ui` serves a
+  point-and-click workspace on **this machine only**: it binds `127.0.0.1` (never
+  off the machine, whatever `TEXTFLOWKIT_ALLOW_REMOTE` is set to) and opens a
+  browser once serving. It mounts the existing developer HTTP app under `/api`
+  **unchanged** — the same routes, submission contract, and job store — and adds
+  only transport: a loopback session layer, a streamed upload, a fixed-format
+  download, in-workspace playback, and a capability endpoint. It adds **no new
+  dependency** beyond the existing `http` extra (FastAPI + uvicorn).
+- **Durable jobs, cancel and resume in the workspace.** Jobs and checkpoints are
+  stored durably under the per-user data directory unless
+  `TEXTFLOWKIT_DB` / `TEXTFLOWKIT_WORK_ROOT` / `TEXTFLOWKIT_OUTPUT_ROOT` is set.
+  A dropped file is streamed and capped at **2 GiB** by default
+  (`TEXTFLOWKIT_UI_MAX_UPLOAD_BYTES` overrides it). A running job can be
+  cancelled, and a durable job resumed.
+- **Windows desktop shortcut.** `textflowkit-ui --create-shortcut` creates a Start
+  Menu entry that launches with `pythonw` (no console) and needs no `pywin32`.
+  Under `pythonw` a startup failure is logged under the per-user data directory
+  and shown in a message box rather than failing silently.
+- **Controlled shutdown that drains.** **Stop server** asks this process's own
+  uvicorn server to exit through its supported `should_exit` flag; the normal
+  lifespan teardown **waits for current jobs to finish** before draining the
+  worker pool rather than interrupting them, so a running job's saved progress
+  survives and is resumable. It never sends a signal to a pid.
+
+### Changed
+
+- **Documentation surfaces.** README, user manual, install notes, developer
+  manual, architecture guide, roadmap, release checklist, site deployment, the
+  landing page, and the checked-in SVG diagrams now describe the local browser
+  interface as a shipped feature and a fifth door, and remove the earlier
+  "unreleased candidate / install from source only" wording.
+- **No endpoint-breaking change.** The CLI, Python API, MCP server, and JSON HTTP
+  adapter are unchanged in this release; the optional engines, diarization, and
+  translation keep their documented dependency requirements.
+
+### Verification boundary
+
+Automated coverage runs the UI's routes, packaging, ownership/shutdown, and
+security boundaries. A **native Windows** machine, in a real browser, proved the
+workspace end to end (drop a file, submit, download, stop). That is one platform's
+browser proof, **not** a live Linux or macOS UI run — those platforms are covered
+by automated tests only, and cross-platform CI (Windows/Linux/macOS) is a separate
+release gate. **No live optional-backend (translation or
+diarization) run through the UI is claimed.** The engine and packaging changes of
+v0.1.9 are unchanged by this release.
+
 ## v0.1.9 — 2026-10-05
 
 **Whistle is now the default engine.** This release ships the Whistle integration

{textflowkit-0.1.9 → textflowkit-0.1.11}/CONTRIBUTING.md

@@ -14,9 +14,15 @@ python -m venv .venv
 # Windows: .venv\Scripts\activate
 # POSIX:   source .venv/bin/activate
 pip install ./packages/textflowkit-fonts  # local optional PDF font companion
-pip install -e ".[dev,mcp,http,export]"
+pip install -e ".[dev,mcp,http,streaming,export,whisper]"
 ```
 
+The full suite needs both `streaming` (WebSocket transport) and `whisper`
+(optional standalone engine) dependencies. Use a development environment; for
+an existing AMD ROCm torch stack, follow [the install guide](docs/install.md)
+to preserve that stack. Native live streaming supports Windows x86_64 only;
+ordinary standalone platform support and defaults remain unchanged.
+
 ## Test and lint — the commands CI runs
 
 ```bash

{textflowkit-0.1.9 → textflowkit-0.1.11}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.5
 Name: textflowkit
-Version: 0.1.9
+Version: 0.1.11
 Summary: Cross-platform media transcription toolkit: URL or file in, timestamped transcripts and subtitle files out.
 Project-URL: Homepage, https://www.textflowkit.org/
 Project-URL: Issues, https://github.com/scottconverse/textflowkit/issues
@@ -32,6 +32,7 @@ Requires-Dist: python-docx>=1.1; extra == 'all'
 Requires-Dist: reportlab>=4.0; extra == 'all'
 Requires-Dist: textflowkit-fonts<0.2,>=0.1.5; extra == 'all'
 Requires-Dist: uvicorn>=0.30; extra == 'all'
+Requires-Dist: websockets<16,>=15; extra == 'all'
 Provides-Extra: dev
 Requires-Dist: build>=1.2; extra == 'dev'
 Requires-Dist: hatchling>=1.25; extra == 'dev'
@@ -53,6 +54,11 @@ Requires-Dist: pydantic>=2.7; extra == 'http'
 Requires-Dist: uvicorn>=0.30; extra == 'http'
 Provides-Extra: mcp
 Requires-Dist: mcp>=2.0; extra == 'mcp'
+Provides-Extra: streaming
+Requires-Dist: fastapi>=0.115; extra == 'streaming'
+Requires-Dist: pydantic>=2.7; extra == 'streaming'
+Requires-Dist: uvicorn>=0.30; extra == 'streaming'
+Requires-Dist: websockets<16,>=15; extra == 'streaming'
 Provides-Extra: whisper
 Requires-Dist: openai-whisper>=20240930; extra == 'whisper'
 Description-Content-Type: text/markdown
@@ -67,7 +73,7 @@ Cross-platform media transcription toolkit. **One core, one CLI, thin adapters.*
 [User manual](https://github.com/scottconverse/textflowkit/blob/main/docs/user-manual.md) ·
 [Developer and integration manual](https://github.com/scottconverse/textflowkit/blob/main/docs/adapters.md)
 
-**Current release: [v0.1.9](https://github.com/scottconverse/textflowkit/releases/tag/v0.1.9).**
+**Current release: [v0.1.11](https://github.com/scottconverse/textflowkit/releases/tag/v0.1.11).**
 
 The [static site deployment](https://github.com/scottconverse/textflowkit/blob/main/docs/site-deployment.md) is hosted on Cloudflare
 Pages. GitHub remains the source and CI host; the website does not run the
@@ -128,10 +134,11 @@ DOCX and PDF are available through the optional `export` extra.
 
 ## Architecture
 
-![TextFlowKit shared-core architecture: four thin entry points (CLI, Python, MCP, HTTP) feed one core that acquires and decodes media, transcribes with the default Whistle engine or an explicitly selected openai-whisper, keeps job state and resume checkpoints in an optional SQLite store, adds optional speaker or translation postprocessing, and publishes TXT, SRT, VTT, JSON, Markdown, and optional DOCX/PDF exports.](https://raw.githubusercontent.com/scottconverse/textflowkit/v0.1.9/docs/assets/architecture-overview.svg)
+![TextFlowKit shared-core architecture: five thin entry points feed one core. The CLI, Python API, MCP, HTTP API, and the local browser UI (a fifth door that mounts the existing HTTP app under /api and shares the same job store, adding transport only, not a new pipeline) sit above one core that acquires and decodes media, transcribes with the default Whistle engine or an explicitly selected openai-whisper, keeps job state and resume checkpoints in an optional SQLite store, adds optional speaker or translation postprocessing, and publishes TXT, SRT, VTT, JSON, Markdown, and optional DOCX/PDF exports.](https://raw.githubusercontent.com/scottconverse/textflowkit/v0.1.11/docs/assets/architecture-overview.svg)
 
-The design principle is **one engine, three doors**. Everything of substance lives in
-the core; the interfaces are thin.
+The design principle is **one shared core, thin doors**. Everything of substance
+lives in the core; the interfaces are thin — the local browser UI is a fifth door
+that adds only transport over the existing HTTP app and shared job store.
 
 | Layer | Path | Responsibility |
 |---|---|---|
@@ -141,6 +148,7 @@ the core; the interfaces are thin.
 | **CLI** | `src/textflowkit/cli.py` | Reference interface (subprocess-friendly) |
 | **MCP** | `src/textflowkit/adapters/mcp_server.py` | stdio + Streamable HTTP, for AI harnesses |
 | **HTTP** | `src/textflowkit/adapters/http_server.py` | JSON API, for software products and web frontends |
+| **Local UI** | `src/textflowkit/ui` | Loopback-only browser workspace over the same HTTP app and job store |
 
 Because the core owns the pipeline, adding a door is cheap — and adding a platform
 means writing one source adapter, not another tool.
@@ -148,6 +156,32 @@ means writing one source adapter, not another tool.
 For the job lifecycle, process ownership, checkpoints, and output publication,
 see [docs/architecture.md](https://github.com/scottconverse/textflowkit/blob/main/docs/architecture.md).
 
+## Live microphone streaming (opt-in)
+
+In v0.1.11, live streaming supports **Windows x86_64 only**. When
+`TEXTFLOWKIT_STREAMING=1` is set, the developer HTTP app serves a `/stream`
+WebSocket and the local UI serves `/api/stream`, both transcribing a live microphone
+as you speak. A **runnable, self-hosted browser example** ships at
+`/streaming-example` (and `/api/streaming-example` under the UI): it captures with an
+`AudioWorklet`, resamples any device rate to 16 kHz mono, and shows the transcript.
+No CDN, no analytics, no external fetch. Requires the `streaming` extra:
+
+```bash
+python -m pip install "textflowkit[streaming]==0.1.11"
+```
+
+It is **off by default** — with the switch unset the endpoint does not exist — and
+**loopback-only**: auth is fail-closed, so the UI accepts only its own origin and
+capability, the standalone API requires `TEXTFLOWKIT_API_TOKEN` (even in developer
+mode), and a separate origin — including the standalone browser example's own origin —
+may stream only if listed in `TEXTFLOWKIT_STREAMING_ORIGINS`. The standalone
+`textflowkit` CLI is unaffected: it does not open a microphone or a streaming socket.
+**Bounded live runs are verified on the native engine here** — 65 s and 300 s
+end-to-end on Windows x86_64; the transport and the browser resampler are covered by
+tests, and a physical browser microphone has not yet been captured (the browser proof
+drives the page against a fake audio device). See
+[docs/streaming.md](https://github.com/scottconverse/textflowkit/blob/main/docs/streaming.md).
+
 ## Recognized sources
 
 YouTube · TikTok · Facebook · Instagram · Vimeo · Twitch · Bilibili · Rumble ·
@@ -294,7 +328,7 @@ textflowkit export ./transcript.json --format vtt
 needs no PyTorch, so a fresh `pip install textflowkit` stays small and pulls no
 torch; `openai-whisper` is an explicitly selectable opt-in engine.
 
-![Whistle bounded block run and durable resume: a decoded PCM WAV is split into 26-second cores with up to 2 seconds of context (each clip ≤ 30 s), each core runs as one owned child with forced telemetry-off flags, a partial checkpoint is written after each core, and a resume validates the source and decoded-WAV hashes then re-runs only the unfinished cores.](https://raw.githubusercontent.com/scottconverse/textflowkit/v0.1.9/docs/assets/whistle-resume.svg)
+![Whistle bounded block run and durable resume: a decoded PCM WAV is split into 26-second cores with up to 2 seconds of context (each clip ≤ 30 s), each core runs as one owned child with forced telemetry-off flags, a partial checkpoint is written after each core, and a resume validates the source and decoded-WAV hashes then re-runs only the unfinished cores.](https://raw.githubusercontent.com/scottconverse/textflowkit/v0.1.11/docs/assets/whistle-resume.svg)
 
 - **CPU only, no torch.** It runs a pinned native binary and downloads one pinned
   model on first use. Naming a GPU device is refused rather than silently
@@ -311,7 +345,7 @@ torch; `openai-whisper` is an explicitly selectable opt-in engine.
   of context on each side, so every standalone clip is ≤ 30 seconds (the native
   CLI's limit). Overlap words are selected by core midpoint rather than text
   deduplication, so repeated spoken phrases are preserved.
-- **Streaming is not used.** The native `--audio-stream` mode failed its
+- **Standalone streaming is not used.** The native `--audio-stream` mode failed its
   coverage and is never passed; only the committed standalone output is parsed.
 - **Durable block resume.** With `TEXTFLOWKIT_DB` set, a long run writes partial
   per-block checkpoints; a resume checks the source and decoded-WAV hashes and the
@@ -397,6 +431,66 @@ contract checks cover it, and running an actual build is deliberately out of
 scope here, so no image is claimed to build or start. See
 [the container example](https://github.com/scottconverse/textflowkit/blob/main/docs/adapters.md#container-example-dockerfile-and-compose).
 
+## Local browser interface
+
+For point-and-click use there is a local browser workspace that runs on **this
+machine only**, reuses the same pipeline and job store, and adds no dependency of
+its own beyond the `http` extra. It ships with the core package as of v0.1.10:
+a regular install of the current release carries it.
+
+```bash
+python -m pip install 'textflowkit[http,export]==0.1.11'
+textflowkit-ui
+```
+
+On Windows you can create a desktop shortcut when you want one:
+
+```powershell
+textflowkit-ui --create-shortcut                 # Start Menu entry (pythonw, no console)
+textflowkit-ui --create-shortcut --shortcut-dir 'C:\path\to\folder'
+```
+
+The shortcut is created only on request and needs no `pywin32`. Under `pythonw`
+there is no console, so a startup failure is written to a log file under the
+per-user data directory and shown in a message box rather than failing silently.
+The normal operator path is to launch from that shortcut; the console command
+above is equivalent.
+
+**This is a local app, not a public website.** The [landing page](https://www.textflowkit.org/)
+is static documentation served by Cloudflare Pages; it does **not** run the
+transcription engine and offers no upload form. The browser workspace exists only
+on the machine that installed it.
+
+- **Loopback only.** It binds `127.0.0.1` (never off the machine, whatever
+  `TEXTFLOWKIT_ALLOW_REMOTE` is set to) and opens a browser once it is serving.
+- **One owner per database.** A second launch against the same database opens the
+  UI already running rather than starting a competing server. **Stop server** in
+  the workspace shuts the local server down without a terminal, waiting for the
+  current jobs to finish rather than interrupting them. Shutdown **drains** — it
+  lets in-flight jobs complete; it does **not** auto-cancel them. Cancel a job
+  first to stop it early.
+- **Durable jobs with cancel and resume.** Jobs and checkpoints are stored
+  durably under the per-user data directory unless you set `TEXTFLOWKIT_DB` /
+  `TEXTFLOWKIT_WORK_ROOT` / `TEXTFLOWKIT_OUTPUT_ROOT`. A dropped file is capped
+  at **2 GiB** by default (`TEXTFLOWKIT_UI_MAX_UPLOAD_BYTES` overrides it).
+  In-workspace playback uses the browser's native player on the **currently
+  selected** media, so it depends on what that browser can decode; it is a
+  convenience preview, not a format guarantee.
+- **No UI analytics.** The page loads no CDN asset and no analytics, and the
+  session token lives only in the page — never in a URL, cookie, or log line.
+- **What uses the network.** The page itself loads nothing remote. A **URL
+  source** is downloaded from the internet; an engine's **model** may be
+  downloaded on first use; and **remote or cloud translation** (an advanced
+  option) sends transcript text to that backend. With local media and a local
+  translation model, no transcript leaves the machine.
+- `--port`, `--no-browser`, and `--version` are available.
+
+The other doors are unchanged: the CLI, Python API, MCP, and HTTP adapters keep
+their existing behavior, and the optional engines, diarization, and translation
+retain their documented dependency requirements. See the
+[user manual](https://github.com/scottconverse/textflowkit/blob/main/docs/user-manual.md#7-local-browser-interface)
+and [architecture guide](https://github.com/scottconverse/textflowkit/blob/main/docs/architecture.md#one-owner-per-database).
+
 ## Durable, bounded, cancellable
 
 ```bash
@@ -411,23 +505,43 @@ boundary. See [docs/adapters.md](https://github.com/scottconverse/textflowkit/bl
 
 The MCP and HTTP adapters are **job-based**: submission returns a job id
 immediately and clients poll for completion. The CLI uses the same core but
-waits for the result. This lets AI harnesses, software products, and a future
-web frontend share the job contract without blocking a request.
+waits for the result. This lets AI harnesses, software products, and the local
+browser interface share the job contract without blocking a request.
 
 ## Status
 
-**v0.1.9 release.** Core, CLI, MCP, and HTTP have automated
-coverage. This release makes **Whistle the default engine** — a native CPU-only
-transcriber that needs no PyTorch — and moves `openai-whisper` to the optional
-`whisper` extra, selected explicitly with `--engine whisper` or
-`engine="whisper"`. Legacy engine aliases are preserved, so older saved jobs and
-`transcribe()` calls still decode. Whistle refuses an unsupported platform,
-language, or GPU request instead of silently falling back. Its engine's
-verification boundary is in [Whistle (default engine)](#whistle-default-engine)
-above. Release publication uses the tag workflow, which requires successful
-exact-commit main CI before PyPI uploads and creates the public GitHub release
-only afterward. Check the linked release for artifacts and workflow status; local
-source verification is not a fresh PyPI-install or individual-harness receipt.
+**v0.1.11 release.** Optional live streaming adds a transport-neutral
+`StreamingSession` Python API, incremental transcript events, and authenticated
+loopback WebSockets (`/stream` on the developer HTTP API and `/api/stream` on the
+local UI), with a packaged browser microphone example. The native live capability
+supports **Windows x86_64 only** and uses one owned child with a separately pinned
+`libneedle3.dll`. The `streaming` extra supplies the WebSocket dependency;
+`TEXTFLOWKIT_STREAMING=1` enables the server routes. Streaming is off by default.
+
+Existing file and URL transcription, CLI, MCP, durable jobs, and local browser
+workspace defaults remain unchanged. Whistle stays the CPU-only standalone default;
+`openai-whisper` remains an explicit opt-in engine. The local browser workspace
+introduced in v0.1.10 still needs only the `http` extra for its ordinary job flow.
+Fonts remain 0.1.6. Live sessions are ephemeral and have no durable resume.
+
+**Streaming evidence.** Local English PCM runs exercised the native core for 65 s
+and 300 s; a separate assembled UI WebSocket run fed prerecorded PCM at real time
+for 12 s and returned incremental events and a final transcript. Browser lifecycle
+and resampling checks used fake audio. Physical browser microphone capture, live
+Linux/macOS, and the six other accepted languages were not verified. The public
+website remains static documentation and serves no streaming endpoint. Local source
+validation does not establish published-package or exact-commit CI results.
+
+**Verification limit.** The local browser interface is covered by an automated
+suite, and the UI's behavior was proved on a **native Windows** machine in a real
+browser. No live optional-backend (translation/diarization) run through the UI is
+claimed, and **no live Linux or macOS UI run was performed here** — those
+platforms are covered by automated tests only, and CI across Windows, Linux, and
+macOS is a separate release gate. Release publication uses the tag
+workflow, which requires successful exact-commit main CI before PyPI uploads and
+creates the public GitHub release only afterward. Check the linked release for
+artifacts and workflow status; local source verification is not a fresh
+PyPI-install or individual-harness receipt.
 
 The v0.1.8 release carried four fixes for the 2026-10-01 post-release audit-lite
 (findings AL-001 – AL-004): CLI owning-process startup recovery so an interrupted
@@ -439,8 +553,8 @@ that precede it. The v0.1.7 source candidate was verified with real CLI, HTTP an
 MCP speech, seven-format exports and completed resume; the v0.1.8 runtime fixes
 were independently checked through fresh-process CLI restart probes, real SQLite
 setup-failure tests, and the full Windows test suite. Those checks are not new
-individual-harness receipts. That is the previous release's record, not evidence
-for v0.1.9.
+individual-harness receipts. That is the previous releases' record, not evidence
+for v0.1.11.
 
 The v0.1.6 release was the post-v0.1.5 review repair set: security hardening
 for media acquisition and the HTTP and MCP adapters, safer subtitle wrapping and
@@ -459,7 +573,7 @@ and both [core](https://pypi.org/project/textflowkit/0.1.6/) and
 [fonts](https://pypi.org/project/textflowkit-fonts/0.1.6/) PyPI projects are
 live — that is the v0.1.6 release's evidence, not a receipt for a later release.
 Everything from here to the end of this section is the v0.1.6 release's
-historical record as published: it is not re-verified for v0.1.9, whose separate release evidence is not supplied by these historical paragraphs.
+historical record as published: it is not re-verified for v0.1.11, whose separate release evidence is not supplied by these historical paragraphs.
 Merged-main CI passed 16/16 on the tagged commit; the published wheel and
 sdist digests match the GitHub release assets and their SHA-256 list; and a fresh
 Windows Python 3.12 install of `textflowkit[export,mcp,http]==0.1.6` from PyPI

{textflowkit-0.1.9 → textflowkit-0.1.11}/README.md

@@ -8,7 +8,7 @@ Cross-platform media transcription toolkit. **One core, one CLI, thin adapters.*
 [User manual](https://github.com/scottconverse/textflowkit/blob/main/docs/user-manual.md) ·
 [Developer and integration manual](https://github.com/scottconverse/textflowkit/blob/main/docs/adapters.md)
 
-**Current release: [v0.1.9](https://github.com/scottconverse/textflowkit/releases/tag/v0.1.9).**
+**Current release: [v0.1.11](https://github.com/scottconverse/textflowkit/releases/tag/v0.1.11).**
 
 The [static site deployment](https://github.com/scottconverse/textflowkit/blob/main/docs/site-deployment.md) is hosted on Cloudflare
 Pages. GitHub remains the source and CI host; the website does not run the
@@ -69,10 +69,11 @@ DOCX and PDF are available through the optional `export` extra.
 
 ## Architecture
 
-![TextFlowKit shared-core architecture: four thin entry points (CLI, Python, MCP, HTTP) feed one core that acquires and decodes media, transcribes with the default Whistle engine or an explicitly selected openai-whisper, keeps job state and resume checkpoints in an optional SQLite store, adds optional speaker or translation postprocessing, and publishes TXT, SRT, VTT, JSON, Markdown, and optional DOCX/PDF exports.](https://raw.githubusercontent.com/scottconverse/textflowkit/v0.1.9/docs/assets/architecture-overview.svg)
+![TextFlowKit shared-core architecture: five thin entry points feed one core. The CLI, Python API, MCP, HTTP API, and the local browser UI (a fifth door that mounts the existing HTTP app under /api and shares the same job store, adding transport only, not a new pipeline) sit above one core that acquires and decodes media, transcribes with the default Whistle engine or an explicitly selected openai-whisper, keeps job state and resume checkpoints in an optional SQLite store, adds optional speaker or translation postprocessing, and publishes TXT, SRT, VTT, JSON, Markdown, and optional DOCX/PDF exports.](https://raw.githubusercontent.com/scottconverse/textflowkit/v0.1.11/docs/assets/architecture-overview.svg)
 
-The design principle is **one engine, three doors**. Everything of substance lives in
-the core; the interfaces are thin.
+The design principle is **one shared core, thin doors**. Everything of substance
+lives in the core; the interfaces are thin — the local browser UI is a fifth door
+that adds only transport over the existing HTTP app and shared job store.
 
 | Layer | Path | Responsibility |
 |---|---|---|
@@ -82,6 +83,7 @@ the core; the interfaces are thin.
 | **CLI** | `src/textflowkit/cli.py` | Reference interface (subprocess-friendly) |
 | **MCP** | `src/textflowkit/adapters/mcp_server.py` | stdio + Streamable HTTP, for AI harnesses |
 | **HTTP** | `src/textflowkit/adapters/http_server.py` | JSON API, for software products and web frontends |
+| **Local UI** | `src/textflowkit/ui` | Loopback-only browser workspace over the same HTTP app and job store |
 
 Because the core owns the pipeline, adding a door is cheap — and adding a platform
 means writing one source adapter, not another tool.
@@ -89,6 +91,32 @@ means writing one source adapter, not another tool.
 For the job lifecycle, process ownership, checkpoints, and output publication,
 see [docs/architecture.md](https://github.com/scottconverse/textflowkit/blob/main/docs/architecture.md).
 
+## Live microphone streaming (opt-in)
+
+In v0.1.11, live streaming supports **Windows x86_64 only**. When
+`TEXTFLOWKIT_STREAMING=1` is set, the developer HTTP app serves a `/stream`
+WebSocket and the local UI serves `/api/stream`, both transcribing a live microphone
+as you speak. A **runnable, self-hosted browser example** ships at
+`/streaming-example` (and `/api/streaming-example` under the UI): it captures with an
+`AudioWorklet`, resamples any device rate to 16 kHz mono, and shows the transcript.
+No CDN, no analytics, no external fetch. Requires the `streaming` extra:
+
+```bash
+python -m pip install "textflowkit[streaming]==0.1.11"
+```
+
+It is **off by default** — with the switch unset the endpoint does not exist — and
+**loopback-only**: auth is fail-closed, so the UI accepts only its own origin and
+capability, the standalone API requires `TEXTFLOWKIT_API_TOKEN` (even in developer
+mode), and a separate origin — including the standalone browser example's own origin —
+may stream only if listed in `TEXTFLOWKIT_STREAMING_ORIGINS`. The standalone
+`textflowkit` CLI is unaffected: it does not open a microphone or a streaming socket.
+**Bounded live runs are verified on the native engine here** — 65 s and 300 s
+end-to-end on Windows x86_64; the transport and the browser resampler are covered by
+tests, and a physical browser microphone has not yet been captured (the browser proof
+drives the page against a fake audio device). See
+[docs/streaming.md](https://github.com/scottconverse/textflowkit/blob/main/docs/streaming.md).
+
 ## Recognized sources
 
 YouTube · TikTok · Facebook · Instagram · Vimeo · Twitch · Bilibili · Rumble ·
@@ -235,7 +263,7 @@ textflowkit export ./transcript.json --format vtt
 needs no PyTorch, so a fresh `pip install textflowkit` stays small and pulls no
 torch; `openai-whisper` is an explicitly selectable opt-in engine.
 
-![Whistle bounded block run and durable resume: a decoded PCM WAV is split into 26-second cores with up to 2 seconds of context (each clip ≤ 30 s), each core runs as one owned child with forced telemetry-off flags, a partial checkpoint is written after each core, and a resume validates the source and decoded-WAV hashes then re-runs only the unfinished cores.](https://raw.githubusercontent.com/scottconverse/textflowkit/v0.1.9/docs/assets/whistle-resume.svg)
+![Whistle bounded block run and durable resume: a decoded PCM WAV is split into 26-second cores with up to 2 seconds of context (each clip ≤ 30 s), each core runs as one owned child with forced telemetry-off flags, a partial checkpoint is written after each core, and a resume validates the source and decoded-WAV hashes then re-runs only the unfinished cores.](https://raw.githubusercontent.com/scottconverse/textflowkit/v0.1.11/docs/assets/whistle-resume.svg)
 
 - **CPU only, no torch.** It runs a pinned native binary and downloads one pinned
   model on first use. Naming a GPU device is refused rather than silently
@@ -252,7 +280,7 @@ torch; `openai-whisper` is an explicitly selectable opt-in engine.
   of context on each side, so every standalone clip is ≤ 30 seconds (the native
   CLI's limit). Overlap words are selected by core midpoint rather than text
   deduplication, so repeated spoken phrases are preserved.
-- **Streaming is not used.** The native `--audio-stream` mode failed its
+- **Standalone streaming is not used.** The native `--audio-stream` mode failed its
   coverage and is never passed; only the committed standalone output is parsed.
 - **Durable block resume.** With `TEXTFLOWKIT_DB` set, a long run writes partial
   per-block checkpoints; a resume checks the source and decoded-WAV hashes and the
@@ -338,6 +366,66 @@ contract checks cover it, and running an actual build is deliberately out of
 scope here, so no image is claimed to build or start. See
 [the container example](https://github.com/scottconverse/textflowkit/blob/main/docs/adapters.md#container-example-dockerfile-and-compose).
 
+## Local browser interface
+
+For point-and-click use there is a local browser workspace that runs on **this
+machine only**, reuses the same pipeline and job store, and adds no dependency of
+its own beyond the `http` extra. It ships with the core package as of v0.1.10:
+a regular install of the current release carries it.
+
+```bash
+python -m pip install 'textflowkit[http,export]==0.1.11'
+textflowkit-ui
+```
+
+On Windows you can create a desktop shortcut when you want one:
+
+```powershell
+textflowkit-ui --create-shortcut                 # Start Menu entry (pythonw, no console)
+textflowkit-ui --create-shortcut --shortcut-dir 'C:\path\to\folder'
+```
+
+The shortcut is created only on request and needs no `pywin32`. Under `pythonw`
+there is no console, so a startup failure is written to a log file under the
+per-user data directory and shown in a message box rather than failing silently.
+The normal operator path is to launch from that shortcut; the console command
+above is equivalent.
+
+**This is a local app, not a public website.** The [landing page](https://www.textflowkit.org/)
+is static documentation served by Cloudflare Pages; it does **not** run the
+transcription engine and offers no upload form. The browser workspace exists only
+on the machine that installed it.
+
+- **Loopback only.** It binds `127.0.0.1` (never off the machine, whatever
+  `TEXTFLOWKIT_ALLOW_REMOTE` is set to) and opens a browser once it is serving.
+- **One owner per database.** A second launch against the same database opens the
+  UI already running rather than starting a competing server. **Stop server** in
+  the workspace shuts the local server down without a terminal, waiting for the
+  current jobs to finish rather than interrupting them. Shutdown **drains** — it
+  lets in-flight jobs complete; it does **not** auto-cancel them. Cancel a job
+  first to stop it early.
+- **Durable jobs with cancel and resume.** Jobs and checkpoints are stored
+  durably under the per-user data directory unless you set `TEXTFLOWKIT_DB` /
+  `TEXTFLOWKIT_WORK_ROOT` / `TEXTFLOWKIT_OUTPUT_ROOT`. A dropped file is capped
+  at **2 GiB** by default (`TEXTFLOWKIT_UI_MAX_UPLOAD_BYTES` overrides it).
+  In-workspace playback uses the browser's native player on the **currently
+  selected** media, so it depends on what that browser can decode; it is a
+  convenience preview, not a format guarantee.
+- **No UI analytics.** The page loads no CDN asset and no analytics, and the
+  session token lives only in the page — never in a URL, cookie, or log line.
+- **What uses the network.** The page itself loads nothing remote. A **URL
+  source** is downloaded from the internet; an engine's **model** may be
+  downloaded on first use; and **remote or cloud translation** (an advanced
+  option) sends transcript text to that backend. With local media and a local
+  translation model, no transcript leaves the machine.
+- `--port`, `--no-browser`, and `--version` are available.
+
+The other doors are unchanged: the CLI, Python API, MCP, and HTTP adapters keep
+their existing behavior, and the optional engines, diarization, and translation
+retain their documented dependency requirements. See the
+[user manual](https://github.com/scottconverse/textflowkit/blob/main/docs/user-manual.md#7-local-browser-interface)
+and [architecture guide](https://github.com/scottconverse/textflowkit/blob/main/docs/architecture.md#one-owner-per-database).
+
 ## Durable, bounded, cancellable
 
 ```bash
@@ -352,23 +440,43 @@ boundary. See [docs/adapters.md](https://github.com/scottconverse/textflowkit/bl
 
 The MCP and HTTP adapters are **job-based**: submission returns a job id
 immediately and clients poll for completion. The CLI uses the same core but
-waits for the result. This lets AI harnesses, software products, and a future
-web frontend share the job contract without blocking a request.
+waits for the result. This lets AI harnesses, software products, and the local
+browser interface share the job contract without blocking a request.
 
 ## Status
 
-**v0.1.9 release.** Core, CLI, MCP, and HTTP have automated
-coverage. This release makes **Whistle the default engine** — a native CPU-only
-transcriber that needs no PyTorch — and moves `openai-whisper` to the optional
-`whisper` extra, selected explicitly with `--engine whisper` or
-`engine="whisper"`. Legacy engine aliases are preserved, so older saved jobs and
-`transcribe()` calls still decode. Whistle refuses an unsupported platform,
-language, or GPU request instead of silently falling back. Its engine's
-verification boundary is in [Whistle (default engine)](#whistle-default-engine)
-above. Release publication uses the tag workflow, which requires successful
-exact-commit main CI before PyPI uploads and creates the public GitHub release
-only afterward. Check the linked release for artifacts and workflow status; local
-source verification is not a fresh PyPI-install or individual-harness receipt.
+**v0.1.11 release.** Optional live streaming adds a transport-neutral
+`StreamingSession` Python API, incremental transcript events, and authenticated
+loopback WebSockets (`/stream` on the developer HTTP API and `/api/stream` on the
+local UI), with a packaged browser microphone example. The native live capability
+supports **Windows x86_64 only** and uses one owned child with a separately pinned
+`libneedle3.dll`. The `streaming` extra supplies the WebSocket dependency;
+`TEXTFLOWKIT_STREAMING=1` enables the server routes. Streaming is off by default.
+
+Existing file and URL transcription, CLI, MCP, durable jobs, and local browser
+workspace defaults remain unchanged. Whistle stays the CPU-only standalone default;
+`openai-whisper` remains an explicit opt-in engine. The local browser workspace
+introduced in v0.1.10 still needs only the `http` extra for its ordinary job flow.
+Fonts remain 0.1.6. Live sessions are ephemeral and have no durable resume.
+
+**Streaming evidence.** Local English PCM runs exercised the native core for 65 s
+and 300 s; a separate assembled UI WebSocket run fed prerecorded PCM at real time
+for 12 s and returned incremental events and a final transcript. Browser lifecycle
+and resampling checks used fake audio. Physical browser microphone capture, live
+Linux/macOS, and the six other accepted languages were not verified. The public
+website remains static documentation and serves no streaming endpoint. Local source
+validation does not establish published-package or exact-commit CI results.
+
+**Verification limit.** The local browser interface is covered by an automated
+suite, and the UI's behavior was proved on a **native Windows** machine in a real
+browser. No live optional-backend (translation/diarization) run through the UI is
+claimed, and **no live Linux or macOS UI run was performed here** — those
+platforms are covered by automated tests only, and CI across Windows, Linux, and
+macOS is a separate release gate. Release publication uses the tag
+workflow, which requires successful exact-commit main CI before PyPI uploads and
+creates the public GitHub release only afterward. Check the linked release for
+artifacts and workflow status; local source verification is not a fresh
+PyPI-install or individual-harness receipt.
 
 The v0.1.8 release carried four fixes for the 2026-10-01 post-release audit-lite
 (findings AL-001 – AL-004): CLI owning-process startup recovery so an interrupted
@@ -380,8 +488,8 @@ that precede it. The v0.1.7 source candidate was verified with real CLI, HTTP an
 MCP speech, seven-format exports and completed resume; the v0.1.8 runtime fixes
 were independently checked through fresh-process CLI restart probes, real SQLite
 setup-failure tests, and the full Windows test suite. Those checks are not new
-individual-harness receipts. That is the previous release's record, not evidence
-for v0.1.9.
+individual-harness receipts. That is the previous releases' record, not evidence
+for v0.1.11.
 
 The v0.1.6 release was the post-v0.1.5 review repair set: security hardening
 for media acquisition and the HTTP and MCP adapters, safer subtitle wrapping and
@@ -400,7 +508,7 @@ and both [core](https://pypi.org/project/textflowkit/0.1.6/) and
 [fonts](https://pypi.org/project/textflowkit-fonts/0.1.6/) PyPI projects are
 live — that is the v0.1.6 release's evidence, not a receipt for a later release.
 Everything from here to the end of this section is the v0.1.6 release's
-historical record as published: it is not re-verified for v0.1.9, whose separate release evidence is not supplied by these historical paragraphs.
+historical record as published: it is not re-verified for v0.1.11, whose separate release evidence is not supplied by these historical paragraphs.
 Merged-main CI passed 16/16 on the tagged commit; the published wheel and
 sdist digests match the GitHub release assets and their SHA-256 list; and a fresh
 Windows Python 3.12 install of `textflowkit[export,mcp,http]==0.1.6` from PyPI