feat: language parameter for potential accent tuning

1 files changed, 23 insertions, 15 deletions

diff --git a/README.md b/README.md
index 6a28641..a5775af 100644
--- a/README.md
+++ b/README.md
@@ -9,7 +9,7 @@ This builds upon [WhiskeyCoder/Qwen3-Audiobook-Converter](https://github.com/Whi
 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.
 
 - Input: `.txt`, `.pdf`, or `.epub`
-- Output: `.mp3`, `.m4b`, `.ogg`, or `.flac`
+- Output: `.m4b`, `.mp3`, `.ogg`, or `.flac`
 - Output a single file or one per chapter
 - Automatic metadata (title/artist/album tags, chapter track numbers) and a generated cover
 - Two voice modes:
@@ -49,7 +49,7 @@ pip install -r requirements.txt
 
 ## Running the Qwen-TTS server
 
-The converter script talks to a Qwen3-TTS Gradio server that is run using `qwen-tts-demo`. Add `--no-flash-attn` if FlashAttention isn't installed (see below). The script expects the custom voice model and base model to be on different ports depending on which you're using:
+The converter script talks to a Qwen3-TTS Gradio server that is run using `qwen-tts-demo`. Add `--no-flash-attn` if FlashAttention isn't installed (see below). The script expects the custom voice model and base model to be on different ports depending on which you're using. The model(s) will automatically download.
 
 ### Custom voice
 
@@ -69,12 +69,10 @@ qwen-tts-demo Qwen/Qwen3-TTS-12Hz-1.7B-Base --ip 127.0.0.1 --port 7861
 
 Put your book files (epub, etc.) in the `input/` folder. Then run the script. The output goes to `output/`.
 
-If a book's output files already exist in `output/`, you are asked at startup whether to reconvert and overwrite them; answer `n` to skip that book. All questions are asked before conversion begins, so the run is unattended once started.
-
 ### Custom voice
 
 ```bash
-python audiobook_converter.py
+python audiobook.py
 ```
 
 Edit `converter/config.py` to change which built-in voice is used.
@@ -88,22 +86,24 @@ CUSTOM_VOICE_INSTRUCT = "Speak naturally and clearly, as if reading a dramatic b
 ### Voice clone
 
 ```bash
-python audiobook_converter.py --voice-clone --voice-sample path/to/reference.wav
+python audiobook.py --clone path/to/reference.wav
 ```
 
 The reference `.wav` should be ~10-15 seconds (3 second minimum, 60 second maximum; ~15 seconds is ideal). Longer is **not** better.
 
-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`.
+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 `--transcription "..."` or skip transcription with `--no-transcription`.
 
-### Options
+## Options
 
-| Flag                          | Description                                                                                           |
-| ----------------------------- | ----------------------------------------------------------------------------------------------------- |
-| `--speed <n>`                 | Playback speed, pitch-preserving (`1.0` = normal). A normal-speed copy is also output.                |
-| `--format {mp3,m4b,ogg,flac}` | Output format (default `mp3`). `m4b` uses AAC audio and has built-in chapters.                        |
-| `--single-file`               | Not m4b: Merge all chapters into a single file (default: one file per chapter).                       |
-| `--voice-sample-text "..."`   | Override whisper auto-transcription with your own manual reference audio transcript. Not required.    |
-| `--no-transcription`          | Skip auto-transcription of the reference audio. Usually worse, but can give a different voice affect. |
+| Flag                          | Description                                                                                |
+| ----------------------------- | ------------------------------------------------------------------------------------------ |
+| `--clone <path>`              | Reference audio (WAV) for voice cloning. Passing this flag switches to voice clone mode.   |
+| `--transcription "..."`       | Override whisper auto-transcription with your own manual reference audio transcript.       |
+| `--no-transcription`          | Skip auto-transcription of the reference audio.                                            |
+| `--speed <n>`                 | Playback speed, pitch-preserving (`1.0` = normal). A normal-speed copy is also output.     |
+| `--format {mp3,m4b,ogg,flac}` | Output format (default `m4b`). `m4b` uses AAC audio and has built-in chapters.             |
+| `--single-file`               | Not m4b: Merge all chapters into a single file (default: one file per chapter).            |
+| `--language <lang>`           | Output language for the synthesized speech. Can add an accent even if the text is English. |
 
 ## Running tests
 
@@ -133,6 +133,14 @@ Official wheels: https://github.com/Dao-AILab/flash-attention/releases (pick `cp
 
 Third-party wheels: https://mjunya.com/flash-attention-prebuild-wheels/ (hosted at https://github.com/mjun0812/flash-attention-prebuild-wheels).
 
+## Tips
+
+Transcription affects the output a lot. Whisper is okay, but does not give perfect transcription. A manual transcription passed `--transcription` is usually better.
+
+Manual transcription, imperfect whisper transcription, and `--no-transcription` each provide different results. Usually the most accurate transcription is the best, but sometimes `--no-transcription` can produce a flat tone that might be preferable for certain voices.
+
+Setting `--language` to the "wrong" language for English text can produce an accent. It is not as strong as cloning a voice with the desired accent.
+
 ## License
 
 MIT