fix(converter): make m4b a single file with embedded chapters

3 files changed, 26 insertions, 46 deletions

diff --git a/README.md b/README.md
index 17568eb..0f0d090 100644
--- a/README.md
+++ b/README.md
@@ -9,8 +9,9 @@ Original project: [https://github.com/WhiskeyCoder/Qwen3-Audiobook-Converter](ht
 
 The converter sends text extracted from your books to a locally running Qwen3-TTS server and assembles the returned audio into a single audiobook file.
 
-- Supported input: `.txt`, `.pdf`, `.epub`
+- Input: `.txt`, `.pdf`, or `.epub`
 - Output: `.mp3` or `.m4b`
+- Output a single mp3 or one per chapter
 - Two voice modes:
   - Custom voice: pre-built speakers
   - Voice clone: clone a voice from a `.wav` reference audio file
@@ -89,47 +90,21 @@ CUSTOM_VOICE_INSTRUCT = "Speak naturally and clearly, as if reading a dramatic b
 python audiobook_converter.py --voice-clone --voice-sample path/to/reference.wav
 ```
 
-The reference .wav should be ~10-15 seconds with a minimum of 3 seconds and maximum of 60 seconds. Longer is not better. ~15 seconds is ideal.
+The reference `.wav` should be ~10-15 seconds (3 second minimum, 60 second maximum; ~15 seconds is ideal).
 
-Whisper will be used automatically to transcribe the reference audio (`faster_whisper` or `whisper`). If no Whisper backend is installed, it falls back to x-vector-only cloning.
+Whisper (`faster_whisper` or `whisper`) is used automatically to transcribe the reference audio; without a Whisper backend it falls back to x-vector-only cloning. Override with `--voice-sample-text "..."` or skip transcription with `--no-transcription`.
 
-To skip automatic transcription explicitly, pass `--no-transcription`. This should be worse, but in my experience may give a preferable flatter tone to certain voices.
+### Options
 
-You can override whisper by passing your own transcription with `--voice-sample-text "What the reference audio says"`
+| Flag                        | Description                                                                               |
+| --------------------------- | ----------------------------------------------------------------------------------------- |
+| `--speed <n>`               | Playback speed, pitch-preserving (`1.0` = normal). A normal-speed copy is also output.    |
+| `--format {mp3,m4b}`        | Output format (default `mp3`). `m4b` uses AAC audio and is always a single file.          |
+| `--single-file`             | Merge all chapters into a single mp3 (default: one mp3 per chapter).                       |
+| `--voice-sample-text "..."` | Transcript of the reference audio (voice clone only).                                     |
+| `--no-transcription`        | Skip auto-transcription of the reference audio (voice clone only).                        |
 
-### Playback speed
-
-Adjust the speed of the final audiobook without changing pitch (uses ffmpeg `atempo` before encoding). The normal-speed audiobook file is also preserved in the output directory.
-
-```bash
-python audiobook_converter.py --speed 0.9
-```
-
-### Output format (mp3 / m4b)
-
-Use `--format` to choose the output container. The default is `mp3`; `m4b` uses AAC audio (ffmpeg `aac`).
-
-```bash
-python audiobook_converter.py --format m4b
-```
-
-### Chapters (EPUB)
-
-Books with chapters (e.g. EPUB) are converted to **one file per chapter** by default. Files are named `output/<Book>_01_<Chapter>.mp3`, `output/<Book>_02_<Chapter>.mp3`, and so on.
-
-To merge all chapters into a single file instead, pass `--single-file`:
-
-```bash
-python audiobook_converter.py --single-file
-```
-
-When the source has chapters and the output is a single `m4b`, chapter markers are embedded so listeners can skip between chapters:
-
-```bash
-python audiobook_converter.py --format m4b --single-file
-```
-
-TXT and PDF files have no chapter structure and always produce a single file.
+Books with chapters (e.g. EPUB) are converted to **one mp3 per chapter** by default, named `output/<Book>_01_<Chapter>.mp3`, `output/<Book>_02_<Chapter>.mp3`, etc.; use `--single-file` to merge them. `m4b` output is always a single file with chapter markers embedded so listeners can skip between chapters. TXT and PDF files have no chapter structure and always produce a single file.
 
 The `chunks/` folder is scratch space for the current book only — it is emptied before and after every conversion, so an interrupted run never affects the next one.
 
diff --git a/audiobook_converter.py b/audiobook_converter.py
index 783a3ce..36bd5c2 100644
--- a/audiobook_converter.py
+++ b/audiobook_converter.py
@@ -86,8 +86,9 @@ Examples:
     parser.add_argument(
         "--single-file",
         action="store_true",
-        help=("Combine all chapters into a single output file. By default books with "
-              "chapters (e.g. EPUB) are converted to one file per chapter.")
+        help=("Combine all chapters into a single mp3. By default books with "
+              "chapters (e.g. EPUB) are converted to one mp3 per chapter. "
+              "Ignored for m4b, which is always a single file.")
     )
 
     args = parser.parse_args()
diff --git a/converter/converter.py b/converter/converter.py
index ce2c351..f63a412 100644
--- a/converter/converter.py
+++ b/converter/converter.py
@@ -99,10 +99,14 @@ class AudiobookConverter:
                 return False
 
             stem = output_name or file_path.stem
-            embed_chapters = (self.output_format == "m4b" and self.single_file
-                              and len(sections) > 1)
-            if embed_chapters:
-                return self._convert_single_m4b_with_chapters(sections, stem, start_time)
+
+            # m4b is always a single file; multi-chapter books get embedded
+            # chapter markers so listeners can skip between chapters.
+            if self.output_format == "m4b":
+                if len(sections) > 1:
+                    return self._convert_m4b_with_chapters(sections, stem, start_time)
+                output_path = config.AUDIOBOOKS_FOLDER / f"{stem}.{self.output_format}"
+                return self._convert_text(sections[0].text, output_path, start_time)
 
             if self.single_file or len(sections) == 1:
                 text = "\n\n".join(section.text for section in sections)
@@ -124,7 +128,7 @@ class AudiobookConverter:
             # Always cleanup, even on failure or interrupt
             audio.cleanup_chunks()
 
-    def _convert_single_m4b_with_chapters(self, sections, stem: str, start_time: float) -> bool:
+    def _convert_m4b_with_chapters(self, sections, stem: str, start_time: float) -> bool:
         """Convert each chapter to audio, then assemble a single m4b with
         embedded chapter markers."""
         chapter_files = []
@@ -250,7 +254,7 @@ class AudiobookConverter:
             print(f"Reference audio: {Path(self.voice_clone_ref_audio).name}")
             print(f"Language: {config.VOICE_CLONE_LANGUAGE}")
         print(f"Output format: {self.output_format}")
-        if self.single_file:
+        if self.single_file and self.output_format == "mp3":
             print("Chapter mode: single file (--single-file)")
         if abs(self.speed - 1.0) >= 1e-6:
             print(f"Playback speed: {self.speed:g}x")