diff --git a/.github/workflows/_run_notebook.yml b/.github/workflows/_run_notebook.yml
index 607b8060..c8b466af 100644
--- a/.github/workflows/_run_notebook.yml
+++ b/.github/workflows/_run_notebook.yml
@@ -22,6 +22,19 @@ on:
         required: false
         type: string
         default: "{}"
+      # A notebook for something that has merged but not shipped pins the
+      # release that will carry it, and pip cannot install a version PyPI does
+      # not have yet. With this, the job says so and stops, instead of failing
+      # on an install nobody can fix from here. The alternative - installing
+      # espnet from git - would check something other than what a reader gets,
+      # which is the one thing tools/README.md says this must not do.
+      # The notebook's own workflow sets it and names the release it waits
+      # for; a run that is still skipping weeks later is a pin nobody
+      # finished.
+      allow_unreleased_pin:
+        required: false
+        type: boolean
+        default: false
 
 permissions:
   contents: read
@@ -45,17 +58,38 @@ jobs:
           python-version: "3.12"
 
       - name: Install
+        id: install
         run: |
           set -euo pipefail
           python -m pip install --upgrade pip
           # the harness itself, before it can be asked anything
           python -m pip install nbclient nbformat ipykernel \
             librosa scikit-learn matplotlib tqdm soundfile editdistance
+          # The release the notebook pins has to be on PyPI. It is not, for a
+          # notebook written between a feature merging and the release that
+          # carries it - see allow_unreleased_pin above.
+          asked=$(python tools/run_notebook.py \
+            "${{ inputs.notebook }}" --print-install)
+          pinned=$(printf '%s\n' $asked \
+            | grep -E '^espnet(\[[a-z,]+\])?==' || true)
+          version=${pinned##*==}
+          if [ -n "$version" ] && ! curl -sf -o /dev/null \
+              "https://pypi.org/pypi/espnet/$version/json"; then
+            if [ "${{ inputs.allow_unreleased_pin }}" != "true" ]; then
+              echo "::error::this notebook pins espnet $version, which is" \
+                "not on PyPI"
+              exit 1
+            fi
+            echo "skip=true" >> "$GITHUB_OUTPUT"
+            echo "espnet $version is not on PyPI yet, so there is nothing to" \
+              "install and nothing to run: this notebook is waiting for that" \
+              "release." >> "$GITHUB_STEP_SUMMARY"
+            exit 0
+          fi
           # then what this notebook's own pip lines ask for. The runner skips
           # those cells, so installing a different espnet from the one a
           # reader gets would make a pass here mean nothing.
-          python -m pip install $(python tools/run_notebook.py \
-            "${{ inputs.notebook }}" --print-install)
+          python -m pip install $asked
           # and what it clones and installs - VERSA and ParallelWaveGAN are
           # on nobody's index. --no-build-isolation because ParallelWaveGAN's
           # setup.py imports pip, which an isolated build does not have.
@@ -66,4 +100,5 @@ jobs:
           fi
 
       - name: Run ${{ inputs.notebook }}
+        if: steps.install.outputs.skip != 'true'
         run: python tools/run_notebook.py "${{ inputs.notebook }}" --timeout 4800
diff --git a/.github/workflows/s2t_align_demo.yml b/.github/workflows/s2t_align_demo.yml
new file mode 100644
index 00000000..38238a0f
--- /dev/null
+++ b/.github/workflows/s2t_align_demo.yml
@@ -0,0 +1,32 @@
+# Demos/s2t_align_demo.ipynb, every Sunday. The badge on this workflow is what
+# the README shows beside that notebook, which is why it has a file of its own:
+# GitHub's badge is per workflow, and cannot show one job of a matrix.
+
+name: s2t_align_demo
+
+on:
+  schedule:
+    # Sundays, 05:00 UTC
+    - cron: "0 5 * * 0"
+  workflow_dispatch:
+  pull_request:
+    paths:
+      - "Demos/s2t_align_demo.ipynb"
+      - "tools/**"
+      - ".github/workflows/s2t_align_demo.yml"
+      - ".github/workflows/_run_notebook.yml"
+
+permissions:
+  contents: read
+
+jobs:
+  run:
+    uses: ./.github/workflows/_run_notebook.yml
+    with:
+      notebook: Demos/s2t_align_demo.ipynb
+      # espnet2.bin.align merged after v.202610.post1 was tagged, so the
+      # release this notebook pins does not exist yet (espnet#6791 cuts it).
+      # Until then the job says so and skips. Delete this line when
+      # 202610.post2 is on PyPI - and if it is still here a month from now,
+      # the pin was never finished.
+      allow_unreleased_pin: true
diff --git a/Demos/README.md b/Demos/README.md
index 5f7d20df..c52ee9c8 100644
--- a/Demos/README.md
+++ b/Demos/README.md
@@ -39,6 +39,7 @@ the answer now.
 | [`asr_demo.ipynb`](asr_demo.ipynb) | [![asr_demo](https://github.com/espnet/notebook/actions/workflows/asr_demo.yml/badge.svg)](https://github.com/espnet/notebook/actions/workflows/asr_demo.yml) | Transcribe speech with OWSM-CTC, and let it work out the language |
 | [`asr_streaming_demo.ipynb`](asr_streaming_demo.ipynb) | [![asr_streaming_demo](https://github.com/espnet/notebook/actions/workflows/asr_streaming_demo.yml/badge.svg)](https://github.com/espnet/notebook/actions/workflows/asr_streaming_demo.yml) | Watch the words appear while the audio is still arriving |
 | [`st_demo.ipynb`](st_demo.ipynb) | [![st_demo](https://github.com/espnet/notebook/actions/workflows/st_demo.yml/badge.svg)](https://github.com/espnet/notebook/actions/workflows/st_demo.yml) | Translate English speech into German, French and Chinese — the same model |
+| [`s2t_align_demo.ipynb`](s2t_align_demo.ipynb) | [![s2t_align_demo](https://github.com/espnet/notebook/actions/workflows/s2t_align_demo.yml/badge.svg)](https://github.com/espnet/notebook/actions/workflows/s2t_align_demo.yml) | Line text up with the audio it was said in, and score how well they agree |
 | [`tts_demo.ipynb`](tts_demo.ipynb) | [![tts_demo](https://github.com/espnet/notebook/actions/workflows/tts_demo.yml/badge.svg)](https://github.com/espnet/notebook/actions/workflows/tts_demo.yml) | Type a sentence, hear it spoken — one English voice, then 128 of them |
 | [`enh_demo.ipynb`](enh_demo.ipynb) | [![enh_demo](https://github.com/espnet/notebook/actions/workflows/enh_demo.yml/badge.svg)](https://github.com/espnet/notebook/actions/workflows/enh_demo.yml) | Pull speech out of noise, and measure how much it helped |
 | [`spk_demo.ipynb`](spk_demo.ipynb) | [![spk_demo](https://github.com/espnet/notebook/actions/workflows/spk_demo.yml/badge.svg)](https://github.com/espnet/notebook/actions/workflows/spk_demo.yml) | Turn a voice into a vector, and score two recordings against each other |
diff --git a/Demos/s2t_align_demo.ipynb b/Demos/s2t_align_demo.ipynb
new file mode 100644
index 00000000..fe0a4ee6
--- /dev/null
+++ b/Demos/s2t_align_demo.ipynb
@@ -0,0 +1,235 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Forced alignment — when each line was said\n",
+    "\n",
+    "[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/espnet/notebook/blob/master/Demos/s2t_align_demo.ipynb) [![s2t_align_demo](https://github.com/espnet/notebook/actions/workflows/s2t_align_demo.yml/badge.svg)](https://github.com/espnet/notebook/actions/workflows/s2t_align_demo.yml)\n",
+    "\n",
+    "You have a recording and the text of what was said. Alignment says *when*:\n",
+    "a start and an end for every line, a time for every token inside it, and a\n",
+    "score for how well the line and the audio agree. That is what makes\n",
+    "subtitles, what cuts a long recording into training utterances, and what\n",
+    "throws away the pairs where the text does not match the audio.\n",
+    "\n",
+    "Nothing is trained here: alignment reads the CTC head of a model that\n",
+    "already exists. CPU is enough. The checkpoint is 4 GB and cached after the\n",
+    "first run."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Install"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install -q \"espnet==202610.post2\" espnet_model_zoo librosa matplotlib"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## A recording, and what was said\n",
+    "\n",
+    "Four utterances, in the order they were spoken. Alignment needs the order;\n",
+    "it does not need the times, which is the whole point."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import librosa\n",
+    "from IPython.display import Audio, display\n",
+    "\n",
+    "!wget -q -O sample.wav https://github.com/espnet/espnet/raw/master/test_utils/ctc_align_test.wav\n",
+    "speech, rate = librosa.load(\"sample.wav\", sr=16000)\n",
+    "display(Audio(speech, rate=rate))\n",
+    "\n",
+    "utterances = [\n",
+    "    \"The sale of the hotels\",\n",
+    "    \"is part of Holiday's strategy\",\n",
+    "    \"to sell off assets\",\n",
+    "    \"and concentrate on property management\",\n",
+    "]\n",
+    "print(f\"{len(speech) / rate:.1f} s of audio, {len(utterances)} utterances\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Aligning\n",
+    "\n",
+    "`ForcedAligner` takes any published checkpoint with a CTC head — an OWSM\n",
+    "one here, but an ASR model works the same way — and returns one segment an\n",
+    "utterance: when it starts, when it ends, and how sure the model is."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from espnet2.bin.align import ForcedAligner\n",
+    "\n",
+    "aligner = ForcedAligner.from_pretrained(\"espnet/owsm_ctc_v4_1B\", device=\"cpu\")\n",
+    "segments = aligner(\"sample.wav\", utterances)\n",
+    "\n",
+    "for s in segments:\n",
+    "    print(f\"{s.start:5.2f} {s.end:5.2f}  {s.score:.3f}  {s.text}\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Inside an utterance\n",
+    "\n",
+    "Each segment carries the tokens it was made of, with a time and a\n",
+    "probability each. Word-level timestamps come from here."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "for token in segments[0].tokens:\n",
+    "    print(f\"{token.start:5.2f} {token.end:5.2f}  {token.score:.3f}  {token.text}\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Seeing it"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import matplotlib.pyplot as plt\n",
+    "import numpy as np\n",
+    "\n",
+    "fig, ax = plt.subplots(figsize=(11, 3))\n",
+    "ax.plot(np.arange(len(speech)) / rate, speech, linewidth=0.4, color=\"#888\")\n",
+    "for i, s in enumerate(segments):\n",
+    "    ax.axvspan(s.start, s.end, color=f\"C{i}\", alpha=0.25)\n",
+    "    ax.text(\n",
+    "        (s.start + s.end) / 2,\n",
+    "        0.85 * speech.max(),\n",
+    "        s.text.split()[0],\n",
+    "        ha=\"center\",\n",
+    "        fontsize=8,\n",
+    "    )\n",
+    "ax.set_xlabel(\"seconds\")\n",
+    "ax.set_yticks([])\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## The score is the point\n",
+    "\n",
+    "`score` is the mean probability of an utterance's tokens: 1.0 is a perfect\n",
+    "match. Text that does not belong to the audio still gets aligned — the\n",
+    "algorithm has to put it somewhere — and the score is how you find out.\n",
+    "\n",
+    "This is alignment-score filtering, which is how OWSM v4 cleaned its training\n",
+    "data: align, then drop the pairs that score badly\n",
+    "([recipe](https://github.com/espnet/espnet/tree/master/egs2/owsm_v4/s2t1))."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "wrong = list(utterances)\n",
+    "wrong[1] = \"the weather today is cold\"\n",
+    "\n",
+    "for s in aligner(\"sample.wav\", wrong):\n",
+    "    print(f\"{s.score:.3f}  {s.text}\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Write the text the way the model writes it\n",
+    "\n",
+    "The score is a probability under *this* model, so the text has to be spelled\n",
+    "the way the model spells it. The same four sentences in capitals — which is\n",
+    "how this recording's reference transcript is written — score zero, because\n",
+    "OWSM's vocabulary has no capitalised words and each one breaks into letters.\n",
+    "The times are still roughly right; the score is not."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "shouted = [u.upper() for u in utterances]\n",
+    "loud = aligner(\"sample.wav\", shouted)\n",
+    "\n",
+    "for s in loud:\n",
+    "    print(f\"{s.score:.3f}  {s.text}\")\n",
+    "\n",
+    "# the first line, as the model reads it\n",
+    "print([t.text for t in loud[0].tokens[:8]])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Where next\n",
+    "\n",
+    "- **From the terminal**: `espnet align sample.wav --text \"The sale of the hotels\"`\n",
+    "- **From an assistant**: the MCP server offers the same thing as an `align` tool\n",
+    "- **Transcription** with the same checkpoint: [`asr_demo.ipynb`](asr_demo.ipynb)\n",
+    "- **The other algorithm**: `espnet2.bin.ctc_segment` is the\n",
+    "  [`ctc_segmentation`](https://arxiv.org/abs/2007.09127) package's, which\n",
+    "  partitions the timeline rather than marking where each token is, and scores\n",
+    "  in log space. `espnet2/bin/asr_align.py` and `s2t_align.py` are its scripts."
+   ]
+  }
+ ],
+ "metadata": {
+  "colab": {
+   "provenance": []
+  },
+  "kernelspec": {
+   "display_name": "Python 3",
+   "name": "python3"
+  },
+  "language_info": {
+   "name": "python"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 0
+}
diff --git a/README.md b/README.md
index 33017eee..69d7cc3a 100644
--- a/README.md
+++ b/README.md
@@ -17,6 +17,7 @@ One per task, flat in [`Demos/`](Demos), each short enough to read in a sitting.
 | [`asr_demo.ipynb`](Demos/asr_demo.ipynb) | [![asr_demo](https://github.com/espnet/notebook/actions/workflows/asr_demo.yml/badge.svg)](https://github.com/espnet/notebook/actions/workflows/asr_demo.yml) | Transcribe speech with OWSM-CTC, and let it work out the language |
 | [`asr_streaming_demo.ipynb`](Demos/asr_streaming_demo.ipynb) | [![asr_streaming_demo](https://github.com/espnet/notebook/actions/workflows/asr_streaming_demo.yml/badge.svg)](https://github.com/espnet/notebook/actions/workflows/asr_streaming_demo.yml) | Watch the words appear while the audio is still arriving |
 | [`st_demo.ipynb`](Demos/st_demo.ipynb) | [![st_demo](https://github.com/espnet/notebook/actions/workflows/st_demo.yml/badge.svg)](https://github.com/espnet/notebook/actions/workflows/st_demo.yml) | Translate English speech into German, French and Chinese — the same model |
+| [`s2t_align_demo.ipynb`](Demos/s2t_align_demo.ipynb) | [![s2t_align_demo](https://github.com/espnet/notebook/actions/workflows/s2t_align_demo.yml/badge.svg)](https://github.com/espnet/notebook/actions/workflows/s2t_align_demo.yml) | Line text up with the audio it was said in, and score how well they agree |
 | [`tts_demo.ipynb`](Demos/tts_demo.ipynb) | [![tts_demo](https://github.com/espnet/notebook/actions/workflows/tts_demo.yml/badge.svg)](https://github.com/espnet/notebook/actions/workflows/tts_demo.yml) | Type a sentence, hear it spoken — one English voice, then 128 of them |
 | [`enh_demo.ipynb`](Demos/enh_demo.ipynb) | [![enh_demo](https://github.com/espnet/notebook/actions/workflows/enh_demo.yml/badge.svg)](https://github.com/espnet/notebook/actions/workflows/enh_demo.yml) | Pull speech out of noise, and measure how much it helped |
 | [`spk_demo.ipynb`](Demos/spk_demo.ipynb) | [![spk_demo](https://github.com/espnet/notebook/actions/workflows/spk_demo.yml/badge.svg)](https://github.com/espnet/notebook/actions/workflows/spk_demo.yml) | Turn a voice into a vector, and score two recordings against each other |
diff --git a/tools/README.md b/tools/README.md
index 2ad9fe13..873d96f6 100644
--- a/tools/README.md
+++ b/tools/README.md
@@ -47,6 +47,29 @@ the install cell an interface, and this is what it supports.
 | `!apt-get install …`, `!cd repo && pip install .` | removed before the notebook is executed, because the runner is not Colab, but not treated as a Python dependency |
 | anything in a markdown cell | it is prose |
 
+### Pinned to a release that is not out yet
+
+A demo for something that has merged but has not shipped pins the release that
+will carry it, and pip cannot install a version PyPI does not have. The
+notebook's workflow says so:
+
+```yaml
+    with:
+      notebook: Demos/s2t_align_demo.ipynb
+      # espnet2.bin.align merged after v.202610.post1 was tagged
+      allow_unreleased_pin: true
+```
+
+and the run stops after installing the harness, with a line in the job summary
+saying which release it is waiting for, rather than failing on an install
+nobody can fix from here. Without the flag, a pin PyPI does not have is an
+error naming the version - a typo should not pass quietly.
+
+What this does **not** do is install espnet from git, for the reason in the
+table above: a pass here would then say nothing about what a reader gets. The
+line is temporary by construction. A run that is still skipping weeks later is
+a pin nobody finished, and the badge is a skip rather than a green tick.
+
 ### Cloned and installed
 
 A tool that is on nobody's index is fetched in two shell lines: