2.0 — Three-Pipeline Architecture + Multilingual Web UI
Three-Pipeline Architecture + Multilingual Web UI
What's New
Features & Improvements
- Three task types with shared foundations — Simple Video (single prompt → single video via Agnes Video API,
t2v/i2v/ti2vid/keyframes), Creative Video (AI screenwriter → storyboards → per-scene videos → edge_tts narration → fine-grained subtitles → concatenation), Manuscript Video (long-text splitting → AI scene prompts → per-segment videos → unified TTS + subtitles → concatenation). - Multilingual Web UI — three-tab single-page frontend (Simple / Creative / Manuscript) with i18n for 中文 / English / Русский / 日本語 / 한국어 / Bahasa Melayu / Bahasa Indonesia.
- Real-time progress — WebSocket push of pipeline progress; task pause, resume, and stop.
- Fine-grained subtitle system — word-level SRT grouping from edge_tts timestamps, CJK multi-line wrapping,
method="caption"rendering with stroke / background / position customization.
Refactoring & Optimizations
- Four-layer architecture —
core/api(Agnes Chat / Image / Video wrappers with retry + polling),core/audio(edge_tts + SRT + moviepy overlay),core/compositor(concatenation / scaling / frame extraction),core/pipelines(three pipeline implementations). - Pydantic v2 data models — typed task subclasses with persistent state serialization and backward-compatible task loading.
- Two-phase manuscript generation — A/B split of video generation for parallelism and faster completion.
Bug Fixes
- MoviePy 2.x compatibility for subtitle
bg_color/position; TTS volume auto-boosted. - CJK font fallback for legacy tasks; bundled fonts shipped for reliable rendering.
- Video frame cap at the Agnes API limit (409 at 720p) with auto-retry for transient failures.
- Single continuous TTS + SRT for the manuscript pipeline, eliminating per-segment padding drift.
- <可选>兼容性 / 配置变更提醒：v1.0
start.sh一键启动已内置 venv 创建与依赖安装，升级后首次运行会自动准备环境。
About Agnes Video Generator
A completely free, open-source AI video generator: turn text into multi-scene AI videos with narration and subtitles.
- Free and open source — no payment, no high-end GPU required
- Text-to-video, image-to-video, digital anchor and image generation
- Powered by free Agnes AI models, rendered entirely in the cloud
- Runs via Web UI, Docker or npm, and supports self-hosting
Related Pages
Release Notes
Changelog for Agnes Video Generator: new features, improvements and bug fixes for every release.
Try Online Demo | Agnes Video
Enter a prompt and generate AI videos and images instantly
Text to Video API — Free AI Video Generation API, No GPU | Agnes Video
Programmatically access Agnes AI's free video models. Text-to-video, image-to-video, and narration APIs. Developer-friendly, zero-cost, no high-end GPU required.
Why you can trust this
Written by a practicing developer and cross-checked against authoritative primary sources such as arXiv papers, vendor technical reports, and the Stanford AI Index.
SandGrid@lcy362
Author of Agnes Video Generator · Full-stack Developer
Independent developer and author of Agnes Video Generator, an open-source (MIT) AI video generation tool built on Agnes AI's free video models. Has helped 1,000+ creators produce AI videos at zero cost. Focused on making video generation models accessible and production-ready; content is based on hands-on practice and primary research.
View on GitHubLast updated：2026-08-21
Ready to Start Creating?
"Making world-class AI belong to everyone." — Bruce Yang. It's completely free, no credit card, and you won't need a high-end GPU. Your first AI video starts at zero cost. Want to use Agnes AI's free video models? This is the easiest way in.
Clone the GitHub repo and launch in 2 minutes