pyVideoTrans
pyvideotrans.com
- Free plan
- Windows
- macOS
- Linux
- Web
- API
- Self-hosted
What pyVideoTrans is
pyVideoTrans is a free, open-source tool for translating videos with clear human speech. It combines speech recognition, subtitle translation, AI dubbing, and video assembly to produce translated audio and subtitles. It can also transcribe speech in batches to timed SRT files, dub subtitles, and translate SRT files while preserving timestamps and formatting. The project lists more than 30 channels, including Faster-Whisper, F5-TTS, Qwen3-ASR, and Edge-TTS, with local offline and online API options. It offers a desktop GUI, WebUI, and command-line interface, alongside guidance for remote access, server deployment, and Docker use. Documented translation options include DeepL, Google Translate, Microsoft Translate, DeepSeek, ChatGPT, Gemini, and LibreTranslate. Speech options include OpenAI, ElevenLabs, Deepgram, Edge-TTS, Azure TTS, and local models. It runs on Windows, macOS, and Linux and is released under GPL-V3 without feature limits or a login requirement. Third-party APIs may incur charges, and users supply their own accounts and keys. It cannot process media without clear human speech or remove hardcoded subtitles.
Who it suits
It suits content creators, educators, and individuals translating spoken videos into multiple languages. It may also fit users who want local model options or a choice of interface.
Good to know, and what to watch
- Automates recognition, translation, dubbing, and video assembly
- Batch SRT workflows preserve timestamps and formatting
- Offers desktop, web, and command-line interfaces
- Free and open source under GPL-V3
- Third-party API use may incur charges
- Requires clear human speech in the media
- Cannot remove hardcoded subtitles
Plans
Every plan and pricepyVideoTrans
Free plan
Getting started
- Open the pyVideoTrans website
- Choose the Windows package or follow source deployment instructions for macOS, Linux or Windows
- Select the desktop GUI, WebUI or command-line interface
- Choose local models or connect an online API channel
- Download required local model files when prompted
- Provide your own third-party API accounts and keys when using those services
Limits to check
The free pyVideoTrans plan costs nothing, is GPL-V3 open source and has no listed feature limits or login requirement. Third-party API charges are paid separately, and some local channels require model downloads.
The verdict
pyVideoTrans combines video translation with batch transcription and subtitle workflows, and offers several interfaces and model channels. Account for API charges and its requirement for clear human speech before choosing it.
Questions people ask
Is pyVideoTrans free?
Yes. The listed plan is free, with GPL-V3 open-source licensing, no feature limits and no login requirement.
Which platforms can run it?
The project supports API, Linux, macOS, self-hosted, web and Windows use. The maker provides a Windows 10/11 package and deployment instructions for macOS, Linux and Windows.
What translation services are available?
Documented channels include DeepL, Google Translate, Microsoft Translate, DeepSeek, ChatGPT, Gemini and LibreTranslate.
Can it work with local models?
Yes. It lists local offline channels and local API options. Some integrated channels require downloading model files on first use.
Do external APIs cost extra?
Potentially. Users pay third-party API charges separately and provide their own accounts and keys; the maker says those keys are stored locally.
What media can it process?
It is intended for audio or video containing clear human speech. It cannot process media with only background music or visuals and cannot remove hardcoded subtitles.
What the maker publishes
- Audience
- The maker identifies content creators, educators, and individual users translating videos into multiple languages as intended users. source
- Free and licensing
- The maker describes the software as open-source and free under GPL-V3, with no feature limits and no login requirement. source
- Hardware
- The maker says the software runs with or without an NVIDIA GPU, with CUDA acceleration available when a supported GPU is configured. source
- Hardware
- The maker says it can run with or without an NVIDIA GPU, with CUDA acceleration available when supported hardware is present. source
- Integrations
- Documented translation channels include DeepL, Google Translate, Microsoft Translate, DeepSeek, ChatGPT, Gemini, and LibreTranslate. source
- Intended users
- The maker identifies content creators, educators, and individual users who want to translate videos into multiple languages as intended users. source
- Interfaces
- The project offers a desktop GUI, WebUI, and command-line interface, and describes remote access, server deployment, and Docker use. source
- Interfaces
- It offers desktop GUI, WebUI, and command-line interfaces for local use, remote access, server deployment, and Docker. source
- Local models
- Some integrated model channels require downloading their model files on first use, while local API channels can call a model service deployed by the user. source
- Model options
- It lists more than 30 channels, including Faster-Whisper, F5-TTS, Qwen3-ASR, and Edge-TTS, with local offline and online API options. source
- Model options
- The software supports local offline models and online APIs, including Faster-Whisper, F5-TTS, Qwen3-ASR, and Edge-TTS among 30+ channels. source
- Other tasks
- It supports batch speech transcription to timed SRT, subtitle dubbing, and batch SRT translation while preserving timestamps and formatting. source
- Other tasks
- It can batch transcribe speech to timed SRT files, synthesize speech from text or subtitles, and translate SRT files while preserving their timecodes and format. source
- Platforms
- The site offers a prepackaged Windows 10/11 download and source deployment instructions for macOS, Linux, and Windows. source
- Pricing and licensing
- The maker describes the software as free and open source under GPL-3, with no feature limits or login requirement; third-party API charges are paid by the user. source
- Privacy
- The website privacy policy says the site may collect IP addresses, browser and device information, cookies, and analytics data. source
- Processing limitation
- The documentation says it can process audio or video containing clear human speech, cannot process material with only background music or visuals, and cannot remove hard subtitles. source
- Processing limitations
- The documentation says it can process audio or video with clear human speech, but cannot process media with no speech or remove hardcoded subtitles. source
- Security
- The website privacy policy says reasonable security measures are used but does not guarantee absolute information security. source
- Speech integrations
- Documented speech recognition and synthesis channels include OpenAI, ElevenLabs, Deepgram, Edge-TTS, Azure TTS, and local models. source
- Support
- The maker provides documentation, tutorials, a Q&A forum, and a technical support page. source
- Support
- The maker provides documentation, tutorials, a Q&A forum, and a contact email. source
- Supported systems
- The maker provides a Windows 10/11 package and source deployment instructions for macOS, Linux, and Windows. source
- Third-party costs
- Use of third-party APIs may incur charges, and users must provide their own accounts and keys, which the maker says are stored locally. source
Checked against the maker's pages on 5 Oct 2026.