Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,16 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: apache-2.0
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
language:
|
| 4 |
+
- en
|
| 5 |
+
- ru
|
| 6 |
+
- it
|
| 7 |
+
- tr
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
Voicecover AI has introduced an AI-powered video translation tool that features voice cloning and lip sync capabilities. This platform enables creators to translate videos into 30 languages, including Arabic, Mandarin, and Spanish, while matching the speaker's lip movements to the translated audio.
|
| 11 |
+
|
| 12 |
+
Building on its previous success with AI animation, Voicecover raised $25 million in Series B funding in 2022, expanding its services for enterprise customers. The AI Video Translate technology is currently free for subscribers, with plans starting at $2 per minute.
|
| 13 |
+
|
| 14 |
+
This tool aims to reduce localization costs for businesses in marketing, entertainment, and social media. Voicecover's proprietary model, Localizer 3000, powers this feature, which is accessible through Voicecover Studio and its API.
|
| 15 |
+
|
| 16 |
+
A model card repository for the video-to-video translation model and API specifications for web service usage will be available soon. Videos can range from 10 seconds to 55 minutes, with a maximum file size of 2GB, and work best with a single subject facing the camera.
|