No cloud, no tokens to pay. Reads a book using a full cast of characters. Quotation attribution detection (for my novel) is at 97.2% accuracy (485/499 quotes identified and assigned correctly). The autofill of character voice descriptions uses the prose to determine how the character sounds.
Employs Gemma 4[1] for the prose analysis (voice fills, quotation detection) and Qwen3 TTS Voice Design[2] for creating voice samples. Runs on an 8GB NVIDIA T1000 GPU card, 96 GB RAM, and a AMD Ryzen 5 7600.
> annotate your text with extra 'stage directions'
Good idea, not something I've considered yet. Wouldn't take much to add it since there's already a feature for selecting a quotation and assigning it an intonation. Same infrastructure could be reused to select arbitrary text and assign stage directions.
Nice! One suggestion: don't just make this apply to text, but also to a specific cursor position (you could say a zero-length text selection where start=end). That's natural if you eg want to say that between one sentence and the next, or one word and the next, you want to insert the sound of a train arriving or a sigh.
thangalin · · focus · HN ↗
<a href="https://www.youtube.com/watch?v=WAeHgE94rVo" rel="nofollow">https://www.youtube.com/watch?v=WAeHgE94rVo
No cloud, no tokens to pay. Reads a book using a full cast of characters. Quotation attribution detection (for my novel) is at 97.2% accuracy (485/499 quotes identified and assigned correctly). The autofill of character voice descriptions uses the prose to determine how the character sounds.
Employs Gemma 4[1] for the prose analysis (voice fills, quotation detection) and Qwen3 TTS Voice Design[2] for creating voice samples. Runs on an 8GB NVIDIA T1000 GPU card, 96 GB RAM, and a AMD Ryzen 5 7600.
[1]: <a href="https://deepmind.google/models/gemma/gemma-4/" rel="nofollow">https://deepmind.google/models/gemma/gemma-4/
[2]: <a href="https://huggingface.co/spaces/Qwen/Qwen3-TTS-Voice-Design" rel="nofollow">https://huggingface.co/spaces/Qwen/Qwen3-TTS-Voice-Design
eru · · focus · HN ↗
Is it possible to annotate your text with extra 'stage directions' that influence how the book is read out?
thangalin · · focus · HN ↗
Good idea, not something I've considered yet. Wouldn't take much to add it since there's already a feature for selecting a quotation and assigning it an intonation. Same infrastructure could be reused to select arbitrary text and assign stage directions.
eru · · focus · HN ↗