Spelling Bee TTS
Spelling Bee TTS is a spelling testing app I wrote for my kids. It uses natural text-to-speech for the prompt and a local large language model to generate definitions and example sentences. It has a built in corpus of ~31,000 words.
The app tracks the user's progress and automatically adjusts the word difficulty level based on how well they're doing.
Install
System dependencies (Ubuntu):
sudo apt install python3-gi gir1.2-gtk-4.0 mpv
System dependencies (macOS with Homebrew):
brew install python gtk4 pygobject3 gobject-introspection mpv
Install with pip:
pip install spelling-bee-tts
Run
On Linux pip creates a application shortcut. Hit your launcher and search for 'spell'. Or to run from the command line:
python3 -m spellingbee
Notes
edge-ttsrequires network access.- You can override the voice with
EDGE_TTS_VOICE(default:en-US-AriaNeural). - Offline sentence generation uses
llama-cpp-pythonwith a local GGUF model.- By default, the app prompts to download Qwen3-4B-Instruct-2507 Q8_0 into the Hugging Face cache on first use.
- Override with
LLM_REPO_IDorLLM_MODEL_PATH. - Optional tuning:
LLM_N_CTX,LLM_THREADS,LLM_N_BATCH,LLM_TEMPERATURE,LLM_TOP_P.
1 maintainer
Metadata
1 maintainer
Release files for spelling-bee-tts 0.4.2
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| spelling_bee_tts-0.4.2.tar.gz | 992.7 kB | Without provenance | Details for spelling_bee_tts-0.4.2.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| spelling_bee_tts-0.4.2-py3-none-any.whl | Python 3 | none | any | Details for spelling_bee_tts-0.4.2-py3-none-any.whl |
Total release size: 2.0 MB
Release files / spelling_bee_tts-0.4.2.tar.gz
| Download URL | spelling_bee_tts-0.4.2.tar.gz |
|---|---|
| Size | 992.7 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
20fc87e610bbf34e2c0efe651fb4354fe05d5985f8e05a4ceceb606b2058c023
|
|
BLAKE2b-256 checksum How to use checksums |
ec604513779429544c39a3a3961192f73888efb1b156d04ab253e3b0ea54ad61
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.13.7
|
Release files / spelling_bee_tts-0.4.2-py3-none-any.whl
| Download URL | spelling_bee_tts-0.4.2-py3-none-any.whl |
|---|---|
| Size | 989.0 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
48d423a50f0688080328b2a2bfd9f7b01e7979e6411f125ae844f3b64d1f9a94
|
|
BLAKE2b-256 checksum How to use checksums |
fa16d8170a21d2a65d03d09f2be93a0051c330abc11271d70c010f09934e194e
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.13.7
|
Security for spelling-bee-tts 0.4.2
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.
