VideoLingo

What is VideoLingo?

VideoLingo runs a full video localisation pipeline in one Streamlit interface: download (including YouTube via yt-dlp), word-level speech recognition and alignment with Qwen3-ASR and ForcedAligner, AI subtitle segmentation, terminology-aware translation through any OpenAI-compatible LLM, and optional dubbing with GPT-SoVITS, OpenAI, Edge TTS, Fish Audio and other TTS back-ends. It outputs subtitle files and subtitled or dubbed videos, and has a local HTTP API for scripted batch jobs.

Where it fits in a 10–200 person business

• Add Chinese or English subtitles to product demos, webinars and training videos
• Dub marketing videos into another language without a studio
• Batch-process a video library through the local HTTP API

These use cases are our editorial suggestions, not claims made by the project.

Can a business use VideoLingo? (license)

This is a plain-English summary of the license text, not legal advice. Third-party models you run with it have their own licenses.

Data & compliance: does VideoLingo phone home?

Checked against the project's own docs and repository on Nov 4, 2026. "Not documented" means we could not find the answer in official sources; it does not mean the feature is missing or that no data is sent. Third-party services you connect (model APIs, vector databases, search engines) have their own data policies. Compare all apps.

What hardware does VideoLingo need?

The project does not publish a minimum CPU/RAM figure, so we leave the official value blank rather than guess.

GPU: The Docker image needs a Linux host with an NVIDIA GPU and the NVIDIA Container Toolkit. Host installs also run on Apple Silicon (MLX) and on CPU (fp32), where the docs say recognition is slow and suggest the smaller 0.6B model.

No CPU, RAM, GPU memory or disk figures are published. The ASR models (Qwen3-ASR 1.7B/0.6B plus ForcedAligner) are several GB and are downloaded on first use. Apple Silicon needs macOS 14 or newer.

Source: github.com/Huanshere/VideoLingo/blob/main/docs/pages/docs/start.en-US.md

How much does it cost to host VideoLingo per month?

How to deploy VideoLingo

Method: Docker (self-built image, NVIDIA GPU)

git clone https://github.com/Huanshere/VideoLingo.git && cd VideoLingo
docker build -t videolingo .
docker run -d --name videolingo --gpus all -p 127.0.0.1:8501:8501 -v videolingo-output:/app/output -v videolingo-history:/app/history -v videolingo-models:/app/_model_cache -v videolingo-cache:/app/.cache -v videolingo-hf:/root/.cache/huggingface videolingo
# without Docker (Windows, macOS, Linux): uv run start.py

From the official instructions: github.com/Huanshere/VideoLingo/blob/main/docs/pages/docs/docker.en-US.md. Always check the source for the current version before you run it.

Known gotchas when self-hosting VideoLingo

• There is no official prebuilt image: you build it from the checkout, and the Dockerfile copies that checkout including config.yaml, so build before adding API keys to the config. source
• Mount the named volumes for output, history and model caches, otherwise results and multi-GB model downloads are lost when the container is replaced. config.yaml and custom_terms.xlsx must be mounted separately to persist. source
• The documented port binding is local-only; the docs say remote access requires an intentionally configured listening address and access controls. source
• Translation needs an OpenAI-compatible LLM that returns the structured JSON the workflow expects; Edge TTS and the ElevenLabs or MAI recognition options send audio or text to online services. source

Alternatives in Speech & translation

• whisper.cpp Fast C/C++ port of OpenAI Whisper speech recognition with a small HTTP transcription server.
• PDFMathTranslate PDF translator that keeps the original layout, formulas, charts and tables.
• Fish Speech Multilingual text-to-speech and voice cloning server (Fish Audio Drama 3 and S2-Pro) with an HTTP API and web UI.
• Meetily Desktop meeting recorder that transcribes and summarizes meetings locally.
• CosyVoice Multilingual LLM-based text-to-speech with zero-shot voice cloning, Chinese dialects and streaming output.
• FunASR Alibaba's speech recognition toolkit with CPU transcription servers, Chinese-strong models and an OpenAI-compatible API.
• LibreTranslate Self-hosted machine translation API with no dependency on Google or DeepL.
• Anarlog Local-first AI meeting notepad that records device audio without a bot joining the call.
• Speaches OpenAI-compatible speech-to-text and text-to-speech server (faster-whisper, Kokoro, Piper).
• Whisper ASR Webservice Whisper speech-to-text as a REST API in one Docker container.
• Scriberr Self-hosted web app that transcribes audio offline, with speaker labels and AI summaries.

Sources

• GitHub repository: github.com/Huanshere/VideoLingo
• Official documentation, Hardware requirements, Gotcha 4: github.com/Huanshere/VideoLingo/blob/main/docs/pages/docs/start.en-US.md
• License text: github.com/Huanshere/VideoLingo/blob/main/LICENSE
• Deploy instructions, Gotcha 1, Gotcha 2, Gotcha 3: github.com/Huanshere/VideoLingo/blob/main/docs/pages/docs/docker.en-US.md
• Hetzner Cloud pricing (cost estimate): www.hetzner.com/cloud/regular-performance
• GitHub stars, commits and releases: GitHub REST API, fetched Nov 4, 2026