diff options
| author | historia <historiavg@proton.me> | 2026-09-09 15:55:06 -0400 |
|---|---|---|
| committer | historia <historiavg@proton.me> | 2026-09-09 15:55:06 -0400 |
| commit | 71f2c85aa5ea2aa5fe5f31537f5979459e82fcdd (patch) | |
| tree | 2bdb01e2d2e4d3bc334c9014cff4cffbb0bcda08 /README.md | |
| parent | 0157ce4a347f9625e1e9d09e2bbf0fbfad722557 (diff) | |
| download | tts-audiobook-generator-71f2c85aa5ea2aa5fe5f31537f5979459e82fcdd.tar.gz | |
feat: instructions options translated automatically by --instructions
Diffstat (limited to 'README.md')
| -rw-r--r-- | README.md | 3 |
1 files changed, 2 insertions, 1 deletions
@@ -65,7 +65,8 @@ cd tts-audiobook-generator | `--output <dir>` | `./output` | Directory to write finished audiobooks to (default: the `OUTPUT_DIR` setting in `app/converter/config.py`, `./output`). | | `--input-file <file>` | `books/dune.epub` | Convert one specific book (`.txt`/`.pdf`/`.epub`) | | `--output-file <file>` | `out/dune.mp3` | Base output path for the audiobook from `--input-file` | -| `--instructions "..."` | `"A warm adult female narrator with a British accent"` | Voice design or style instruction. Usually used for voice design models, some clone models also accept this. | +| `--instructions "..."` | `"A warm adult female narrator with a British accent"` | Voice design or style instruction. Usually used for voice design models, some clone models also accept this. Families that read it as a request option (e.g. `--option instructions=` like BreezeTTS) get it translated automatically. | + | `--speed <n>` | `1.0` | Playback speed, pitch-preserving (`1.0` = normal). A normal-speed copy is also output. Defaults to the `SPEED` setting in `app/converter/config.py`. | | `--single-file` | | Merge all chapters into a single file. `m4b` is always one file. | | `--language <lang>` | `English` | Output language for the synthesized speech. May add an accent even if the text is English. | |