Video subtitle generation, translation, and multi-format export — browser-based, no CLI required.
Upload a video or audio file. ASR transcribes speech with timestamps. MT translates segments. Export SRT, VTT, ASS, or TXT — with optional bilingual mode.
- 🎬 Video / audio upload — MP4, MOV, AVI, MKV, WebM, MP3, WAV
- 🎙️ Multi-provider ASR — OpenAI Whisper, DashScope Paraformer, Groq Whisper
- 🌐 Multi-provider MT — OpenAI-compatible APIs, DashScope, Anthropic Claude
- 🔊 Optional TTS dubbing — OpenAI TTS or DashScope CosyVoice
- ✏️ Inline segment editor — fix transcription or translation before export
- 📥 Multi-format export — SRT / VTT / ASS / TXT
- 🈯 Bilingual subtitle mode — source + translation in one file
- 🌍 12 languages — ZH, EN, JA, KO, FR, DE, ES, PT, RU, AR, TH, VI
Upload → [ASR] Transcribe → [MT] Translate → [Edit] → Export
↓
[TTS] Dub (optional)
git clone https://github.com/Grayson0130/videotrans.git
cd videotrans
npm install
npm run dev
# → http://localhost:3002| Provider | Model | Notes |
|---|---|---|
| OpenAI Whisper | whisper-1 |
Standard accuracy |
| DashScope | paraformer-realtime-v2 |
Excellent for Chinese |
| Groq Whisper | whisper-large-v3-turbo |
Fastest |
| Provider | Example model |
|---|---|
| OpenAI / DashScope / Groq / DeepSeek | gpt-4o-mini, qwen-plus |
| Anthropic Claude | claude-3-5-haiku-20241022 |
| Provider | Voices |
|---|---|
| OpenAI TTS | alloy, echo, fable, onyx, nova, shimmer |
| DashScope CosyVoice | longxiaochun, longwan, longfei |
| Format | Use case |
|---|---|
.srt |
Most video players, YouTube |
.vtt |
Web players, HTML5 video |
.ass |
Advanced styling, fansubs |
.txt |
Plain transcript, no timecodes |
Next.js 14 · TypeScript · openai SDK · @anthropic-ai/sdk
MIT © Jinhui Zhao