Files

Paul Bailey e6f4e2ea32 Implement TTS service with Kokoro integration

- Created TTSService class with pipeline caching per language
- Implemented text segmentation to identify role markers (colon and bracket patterns)
- Implemented segment synthesis with voice assignment
- Implemented audio concatenation at 24 kHz sample rate
- Added fallback to default voice (af_bella) for unmapped roles
- Supports language codes: a, b, f, j
- Handles long text by chunking on sentence boundaries
- Added comprehensive unit tests (13 tests, all passing)

Requirements: 10.1, 10.3, 10.4, 6.2, 6.3, 6.4, 6.5, 6.6

2025-12-09 01:06:59 +00:00

services

Implement TTS service with Kokoro integration

2025-12-09 01:06:59 +00:00

.env.example

Task 1: Set up project structure and dependencies

2025-12-09 00:47:44 +00:00

.gitignore

Task 1: Set up project structure and dependencies

2025-12-09 00:47:44 +00:00

main.py

Implement role detection service with pattern matching

2025-12-09 01:04:09 +00:00

README.md

Task 1: Set up project structure and dependencies

2025-12-09 00:47:44 +00:00

requirements.txt

Task 1: Set up project structure and dependencies

2025-12-09 00:47:44 +00:00

test_api.py

Implement backend API foundation

2025-12-09 00:57:46 +00:00

test_role_detection.py

Implement role detection service with pattern matching

2025-12-09 01:04:09 +00:00

test_tts_service.py

Implement TTS service with Kokoro integration

2025-12-09 01:06:59 +00:00

README.md

Text to Audiobook Backend

FastAPI backend service for converting text to multi-voice audiobooks using Kokoro TTS.

Setup

Prerequisites

Python 3.10 or higher
espeak-ng (system dependency)

Install espeak-ng

macOS:

brew install espeak-ng

Linux (Ubuntu/Debian):

sudo apt-get update
sudo apt-get install espeak-ng

Python Environment Setup

Create a virtual environment:

python -m venv venv

Activate the virtual environment:

# macOS/Linux
source venv/bin/activate

# Windows
venv\Scripts\activate

Install dependencies:

pip install -r requirements.txt

Create environment file:

cp .env.example .env

Running the Server

uvicorn main:app --reload --host 0.0.0.0 --port 8000

The API will be available at http://localhost:8000

API documentation: http://localhost:8000/docs

API Endpoints

GET /api/health - Health check endpoint
POST /api/tts/roles - Detect roles in text
POST /api/tts - Generate audiobook