Views
No views yet
| Variant | Size | Tokens/s | Real-time factor |
|---|---|---|---|
| bf16 | 6.2 GB | ~51 tok/s | 0.50x |
| 8-bit | 3.3 GB | ~91 tok/s | 0.82x |
| 4-bit | 1.8 GB | ~108 tok/s | 1.58x |
1# From a text file
2uv run tts.py input.txt -o output.wav
3
4# From stdin
5echo "Hello world" | uv run tts.py - -o hello.wav
6
7# With a custom voice description
8uv run tts.py input.txt -o output.wav -d "Deep male voice, British accent, slow pacing."| Option | Default | Description |
|---|---|---|
input | (required) | Input text file path, or - for stdin |
-o, --output | output.wav | Output WAV file path |
-d, --description | Calm/clear female voice | Voice description prompt |
-m, --model | . | Path to MLX model directory |
--max-chars | 200 | Max characters per chunk |
--max-tokens | 2048 | Max tokens per chunk |
--temperature | 0.4 | Sampling temperature |
--top-p | 0.9 | Top-p sampling |
--repetition-penalty | 1.1 | Repetition penalty |