pyVideoTrans

pyVideoTrans translates spoken video into another language for people preparing subtitles and dubbed versions. It works from the audio, so footage doesn't need existing subtitles.

• Video translation: Produce a video with translated subtitles and AI dubbing, with pauses for proofreading during recognition, translation and dubbing.
• Speaker voices: Distinguish speakers and assign separate dubbing voices, or clone voices with models such as F5-TTS, CosyVoice and GPT-SoVITS.
• Standalone audio and subtitles: Batch transcribe audio or video into SRT files, translate existing subtitles and generate speech from text.
• Media editing tools: Separate vocals, merge subtitles with video and adjust audio-video alignment.

Local processing can use Faster-Whisper for transcription, Ollama or M2M100 for translation, and locally deployed speech models for dubbing. With local models, processing can stay on your hardware and run offline. Cloud options such as ChatGPT, DeepSeek, OpenAI and Azure send the relevant work to external APIs and require provider credentials and any applicable fees.

The application is free and open source under GPL-3.0, runs on Windows, macOS and Linux, and doesn't require an application account. It has a desktop interface and command-line support for batch work and self-hosted servers, including Docker deployment. The optional WebUI provides browser access remotely or over an internal network; it isn't installed locally by default. An NVIDIA GPU is optional and can accelerate processing through CUDA.