diff options
Diffstat (limited to 'README.md')
| -rw-r--r-- | README.md | 26 |
1 files changed, 11 insertions, 15 deletions
@@ -34,30 +34,26 @@ cd tts-audiobook-generator 2. Put your files in the directories -- `./input` - Text files to be processed (`epub`, etc.) -- `./output` - Audio files will output here -- `./voices` - `.wav` files of voices to clone (10-20 seconds) +`./input` - Text files to be processed (`epub`, etc.)\ +`./output` - Audio files will output here\ +`./voices` - `.wav` files of voices to clone (10-20 seconds) -These directories (and output format, language, speed, debug, and more) can be changed any time in `app/converter/config.py` or the TUI's **Settings** menu. +3. Run `python audiobook.py`. It will automatically create a virtual environment and install its requirements. -3. Run `audiobook.py`. It will automatically create the app's virtual environment and install its requirements (each pip-installed TTS backend later gets a managed venv of its own under `app/envs/`). -``` -python audiobook.py -``` +4. Go to `Configure Backends > Install Backend > audio.cpp`. This backend supports numerous TTS models. -4. When the TUI comes up, go to `Configure Backends > Install Backend`. Install `audio.cpp`, which supports numerous TTS models. If you have your own backend server you want to connect to, instead just configure the API URL in settings and you're done. +5. Use the wizard to install one or more TTS models. -5. On the "Select TTS Models to Host" screen, install one or more TTS models. `qwen3_tts_1_7b_base_q8_0` is a good model for cloning and `qwen3_tts_1_7b_customvoice_q8_0` is good for built-in speakers. +`qwen3_tts_1_7b_base_q8_0` is a good model for cloning.\ +`qwen3_tts_1_7b_customvoice_q8_0` is good for built-in speakers. -6. The script will simultaneously build audiocpp_server and download the model files. This will take a while. +6. The script will build audiocpp_server and download models. -7. Go to `Generate Audiobooks` in the main menu to process the input files into audiobooks. The program will automatically start and stop the necessary backend server. +7. Go to `Generate Audiobooks` in the main menu to process the input files into audiobooks. The script will automatically start and stop the necessary backend server. ## CLI Options -Everything the TUI does can also be scripted with flags: `python audiobook.py --backend audiocpp --model higgs --voice narrator`. To convert a single book file instead of the whole input directory, pass `--input-file` (and optionally `--output-file`): `python audiobook.py --input-file books/dune.epub --output-file out/dune.mp3`. The directory flags (`--input`/`--output`) and the single-book flags (`--input-file`/`--output-file`) are mutually exclusive pairs — mixing one stops with an error explaining both. - -Note: unlike the TUI, the CLI does **not** start or stop backend servers — point it at a server that is already running. You can manually launch servers in the TUI too. +Note: unlike the TUI, the CLI does **not** start or stop backend servers. You point it at a server that is already running with `--api-url`. You can manually launch local servers in the TUI too. ```bash python audiobook.py --backend audiocpp --model qwen3_tts_1_7b_base_q8_0 --voice narrator |