yapit-tts/yapit
Listen to anything. TTS for documents, papers, and web pages.
Leverages vision-based document layout detection (DocLayout-YOLO) to extract and semantically parse complex PDFs with math equations, tables, and citations—converting them to spoken descriptions rather than raw text. Supports pluggable TTS backends via OpenAI API compatibility, enabling local synthesis (Kokoro) or premium voices, plus scalable GPU workers via Redis job queue for distributed processing. Also exports clean markdown via URL endpoints (`/md`, `/md-annotated`) and integrates vision models (Gemini, vLLM-compatible APIs) for AI-powered document extraction.
Available on PyPI.
Stars
4
Forks
—
Language
Python
License
AGPL-3.0
Category
Last pushed
Mar 16, 2026
Commits (30d)
0
Dependencies
2
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/yapit-tts/yapit"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
kxxt/aspeak
A simple text-to-speech client for Azure TTS API.
fishaudio/fish-audio-python
The official Python library for the Fish Audio API.
aahl/zai-tts
🗣️ ZAI/GLM TTS to OpenAI Speech API, 免费的语音合成API，支持克隆音色，基于智谱TTS
Aivis-Project/aivmlib
Aivis Voice Model File (.aivm/.aivmx) Utility Library
simonw/ospeak
CLI tool for running text through OpenAI Text to speech