Skip the blank prompt
Image, video, and cover templates created by our team and curated from popular third-party sources, with example results, prompts, and settings.
Choose a template Adjust settings Create
OPEN SOURCE · LOCAL FIRST · BUILT FOR CREATORS
One workspace.
Every kind of creation.
Turn ideas into videos, images, voiceovers, and translations with AI Agents. Go from a single prompt to a finished piece without switching tools.
12,029 GitHub Stars from creators and developers in 100+ countries and regions
Agent poweredLocal dataMultiple models
Say what you want. Watch it happen.
Describe what you need in the composer. OpenCreator prepares the settings and result, then you can refine subtitles, styles, and output in the editor.
OpenCreator
VIDEO TRANSLATION
What would you like to create?
Your request becomes the translation, subtitle, and dubbing settings.
Video translation workspace
ted-interview.mp4 · 6 subtitles
00:00 / 00:25
A local interactive demo. No video upload or model request.
Seedream 5.0 Pro
GPT Image 2.5
Nano Banana 2.1
GPT Image 2.5
Nano Banana 2.1
GPT Image 2.5
OpenCreator charactersTemplates to start. Skills to scale.
108 creation templates and a growing library of Agent Skills, so you never start from a blank prompt.
Give your Agent a way to work
Reuse workflows for subtitles, dubbing, covers, and rendering. Write your own SKILL.md to connect the tools you already use.
krillinai-subtitleSubtitles & translationkrillinai-ttsVoice & dubbingkrillinai-coverCover creationkrillinai-render-vertical9:16 for Shorts & Reels
Install the Skill and configure any services it needs before use.
Codex-native Agent
One conversation drives every workspace: describe the change, and it fills in the settings.
Local-first and open source
Projects, files, and history stay on your machine. Apache-2.0 on GitHub.
The best model for every creative task
Leading image, video, and audio models in one studio. The Agent picks the best one for each step, or you choose.
Video
Seedance 2.5
Cinematic shots with real camera moves and sound. Restyle, extend, and edit any shot.
Image
GPT Image 2.5
Posters, covers, and layouts with type that actually reads.
Image
Nano Banana 2.1
Photoreal scenes and fast edits that keep characters consistent.
Audio
CosyVoice
Natural Chinese and multilingual dubbing, with voice cloning from a short sample.
Audio
Whisper
Accurate transcription that becomes timed subtitles, locally or in the cloud.
Image
- GPT Image 2.5
- Nano Banana 2.1
- Seedream 5.0 Pro
- Seedream 4.0
- Kling v2.1
Video
- Seedance 2.5
- Kling v2.1 Master
- Veo 3.1
Audio
- CosyVoice
- Whisper
- OpenAI TTS
- MiniMax Voice
- Edge TTS
- Aliyun Speech
Language models
- GPT
- DeepSeek
- Qwen
- Kimi
- GLM
- Grok
- Doubao
- ERNIE
- Hunyuan
- MiniMax
Codex powers the Agent. Creative services are configured separately; availability depends on your account, service setup, and platform. Local transcription also supports faster-whisper, WhisperKit, and whisper.cpp. Video translation supports Volcengine ASR / TTS. Cases are creator-published examples.
See more examplesBuilt by theopen source community
Open source · Apache-2.0
- GitHub stars
- 12.0K
- Contributors
- 21
- Countries and regions
- 100+
- Models supported
- 24+
Loading contributor avatars.
Built in the open by 21 contributors. Join them
Frequently asked questions
Quick answers about setup, data, and model services.
What is OpenCreator
OpenCreator is an open-source AI workspace for creators that brings Agents, video, images, voice, translation, and smart editing into one creative workflow.
Which operating systems are supported
Installers are currently available for macOS on Apple silicon, macOS on Intel, and 64-bit Windows 10 or 11. A Linux desktop build is not yet available.
Does my creative data leave my device
Projects, attachments, and runtime logs stay local by default. When you use an online model, the content required for that request is sent to your configured model provider.
What do I need to get started
After installing the desktop app, sign in to Codex or configure the model service used by the Agent, then add any required API Key, Base URL, and model under AI Services. Some services, including Edge TTS, do not require an API Key.
Can I use my own model provider
Yes. Text, image, video, voice, and transcription services can be configured independently, including services compatible with the OpenAI API.
Is OpenCreator open source
Yes. OpenCreator is licensed under the Apache License 2.0, and its source code is available on GitHub. Third-party models and external services may charge according to their own pricing.
How many languages does video translation support?
Video Translation offers 123 source languages and 124 target options, including Pinyin output. Speech recognition and dubbing coverage depend on the selected service and model; not every model supports every language.
Can I translate an SRT file without uploading a video?
Yes. Choose Translate subtitles in Video Translation, import an SRT file, and preview and translate it without a source video, dubbing, or video rendering. Read the SRT translation guide.
Can I edit subtitles after translation?
Yes. Open Advanced editing to adjust subtitles alongside video playback, a waveform and timeline. Find and replace text, change subtitle styles, dubbing and output settings, then generate a new version while keeping previous results.
Is OpenCreator free, and how is model usage charged?
The OpenCreator desktop app is free and open source. With your own API keys, model usage follows your provider’s pricing. Official model services use credits based on the applicable plan and actual usage. See credits and usage details.
Create withOpenCreator
Free for macOS and Windows. Bring your own models, or use ours.