UmbraAudio Review

DealHunterShip_4.0e_whole-to-audio.docx

.umbra/uploads/DealHunterShip_4.0e_whole-to-audio.docx · Status: analyzed

1
Upload
Parse manuscript
2
Scan
Review markers
3
Discover
Find speakers
4
Voices
Generate samples
5
Segment
Split utterances
6
Generate
Build audiobook
7
Export
M4B + MP3

GPU Model Management

Control which models are loaded in GPU memory. Only one model type can be loaded at a time.

Qwen3-TTS Server (CPU Only)

VoiceDesign (1.7B)
Base Clone (1.7B)

LM Studio (LLM)

qwen/qwen3.5-9b (qwen/qwen3.5-9b) ctx=32512
Pipeline GPU Usage Guide
Pipeline Stage → GPU State:
📖 Analysis (BookNLP + LLM profiling) → LM Studio loaded, Qwen unloaded
🎭 Voice Design (generate voice refs) → Qwen VoiceDesign loaded, LM Studio unloaded
✂️ Segmentation (manifests) → Both unloaded
🔊 Generation (TTS synthesis) → Qwen Base loaded, LM Studio unloaded
📦 Export → Both unloaded

Manual controls above override automatic management.

Full Pipeline

Runs all steps automatically: Discover → Voices → Segment → Generate → Export

Step 1 Complete

Manuscript Uploaded

35 chapters loaded

Step 2 Complete

Scan Results

File
DealHunterShip_4.0e_whole-to-audio.docx
Format
DOCX
Chapters
35
Scenes
51
Marker Tags [book start] ✓ [author note] ✓ [toc] ✓ [chapter] ✓ [back matter] ✓
Step 3 Complete

Speakers Discovered

Review Speakers

61 speakers found

Step 4 Complete

Voice Samples Generated

Review Voices

94 voice references ready

Step 5 Complete

Utterances Segmented

Review Chapters

4399 utterances across 35 chapters

Step 6: Generate Audiobook

Generate audio for all utterances using the assigned voices.

Step 7: Export Audiobook

Requires audio generation to complete. Exports to M4B and MP3.

35
Chapters
51
Scenes
61
Speakers
94
Voice Samples
4399
Utterances
0
Audio Generated