OrcaDub 1.0 launches speech-to-speech video dubbing with 4.83 MOS
qinzytech · x · 2026-07-28
OrcaDub 1.0 aims at production-grade speech-to-speech video dubbing
OrcaDub says its new model can localize videos end to end while preserving voice identity, emotion, prosody, timing, and lip sync.
Reported results
- 4.83/5 MOS
- 96.8% speaker similarity
- 92.7 COMET
- 3.1% WER
- 98.5% speaker attribution
What it offers
- Speech → speech dubbing
- Emotion and prosody preservation
- Idiom-aware localization
- Song translation
- Per-word forced alignment
- Background-music preservation
- Free web studio for post-editing
- OpenAI-compatible API
The service is available now with PAYG pricing at $0.60/minute and 10 free minutes.
More from Multimodal
- Third-party test: Claude Opus 5.5 renders finer 3D scenes but costs 13x more than GPT-6 Sol — testingcatalog · 2026-09-23
- ComfyUI trick: aux preprocessor + Qwen transfers poses across characters with one prompt — Acceptable-Work8202 · 2026-09-23
- Same portrait prompt across Midjourney V6.1, V7 and V8.2: do older models look better? — tisch_eins · 2026-09-23
- Testing AI character consistency across a 20-image travel sequence — SiennaVaire · 2026-09-23
- Midjourney v8.2 Faces: New Portrait Generation Samples Shared — azed_ai · 2026-09-23
- One-sentence prompt generates lifelike dog video, shown side-by-side with the real one — wgrathwohl · 2026-09-23