From 6ccb6d443d2fb871b43d96ea61a95bc3e6a92355 Mon Sep 17 00:00:00 2001 From: historia Date: Wed, 26 Aug 2026 17:46:48 -0400 Subject: feat: combined install/configure tui screens into one menu, removed extraneous wizard screens --- README.md | 18 ++++++++++++++---- 1 file changed, 14 insertions(+), 4 deletions(-) (limited to 'README.md') diff --git a/README.md b/README.md index 7d87c5c..8e95659 100644 --- a/README.md +++ b/README.md @@ -39,15 +39,16 @@ cd tts-audiobook-generator - `./output` - Audio files will output here - `./voices` - `.wav` files of voices to clone (10-20 seconds) -3. Run `audiobook.py`. It will create a venv `./app/envs/tts` and automatically install all requirements. - +3. Run `audiobook.py`. It will automatically created a virtual environment and install its requirements. ``` python audiobook.py ``` -4. When the TUI comes up, go to `Configure Backends > Install Backend`. Install `audio.cpp`, which supports numerous TTS models. It will automatically be cloned and built in the venv (this will take a while) — the clone runs in the TUI, and after you pick your models the build and the model downloads run **simultaneously** in a split view (with a status and progress bar for each), so you're never dropped to the console. Uninstalling a backend (`Configure Backends > Uninstall Backend`) asks for confirmation and likewise runs inside the TUI. If a download fails or is interrupted, `Configure Backends > Download Missing Models` re-runs it. +4. When the TUI comes up, go to `Configure Backends > Install Backend`. Install `audio.cpp`, which supports numerous 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. -5. Choose TTS models to install. `Qwen3-TTS` is a popular. Pick the `Base` model if you're cloning voices or `CustomVoice` for built-in TTS. +6. Run through the rest of the wizard. The defaults are probably all correct. The script will simultaneously build audiocpp_server and download the model files. This will take a while. ## CLI Options @@ -86,6 +87,15 @@ If the TUI auto-install doesn't work, you may need to set up the backends manual `./audiobook.py` can also connect to external servers running these backends. Point the relevant `*_REMOTE_URL` in `app/converter/config.py` (or the **Settings** → remote URL fields) at the server's `host:port` — the hub probes it and offers a `[remote]` entry in **Generate audiobooks…** next to the managed one. The defaults are the local ports (`127.0.0.1:`), so a server started outside this tool on the local port is picked up automatically. For scripting, `--api-url` targets any server directly. +## Development + +The test suite runs against any Python that has the app's dependencies +(the managed venv works fine): + +```bash +pytest app/tests # from the repo root +``` + ## Tips Transcription affects the output a lot. Whisper does not always give perfect transcription. Manual transcription is better. -- cgit v1.2.3