1. How do I submit a project for dubbing?
Answer: Navigate to the left side bar of the portal and click on "Create New". From there select "New Video" and fill in all the required fields. Then click on "Dub Project" button on the bottom right.
For assistance, refer to our detailed guide here.
2. What languages are available for dubbing?
Answer: We offer a variety of languages for dubbing. Please take a look at our language options here for the complete list.
3. How long does it take to complete a dubbing project?
Answer: Turnaround times vary based on the project's complexity. Check our estimated delivery times here for more information.
4. What are the pricing plans for dubbing services?
Answer: Our pricing structure depends on the project specifications. Sign up on our platform for pricing details on https://studio.camb.ai/ or contact our sales team for customized quotes ([email protected])
5.How do I reset my password?
Answer: To reset your password, navigate to the login page and click on "Forgot Password." For a detailed walkthrough, please refer to our Password Reset Guide.
6. Why are some of my dubbed dialogues too fast?
Answer: If you notice that some of your dubbed dialogues are too fast, it might be related to timing adjustments during processing. For more information on resolving this issue, please refer to our article: Some of My Dubbed Dialogues Are Too Fast.
7. Can I integrate your service with third-party applications?
Answer: Yes, our platform supports integration with various third-party applications. For a list of supported integrations and setup instructions, please contact our support team at [email protected].
8. How can I fix gaps in my dubbed content?
Gaps in dubbed content can occur due to variations in language length or pacing. For detailed instructions on how to close gaps and improve synchronization, please refer to our Dialogue Edit Options article.
9. Learn more about MARS
We present MARS6, a robust encoder-decoder transformer for rapid, expressive TTS. MARS6 is built on recent improvements in spoken language modelling. Utilizing a hierarchical setup for its decoder, new speech tokens are processed at a rate of only 12 Hz, enabling efficient modelling of long-form text while retaining reconstruction quality. We combine several recent training and inference techniques to reduce repetitive generation and improve output stability and quality. This enables the 70M-parameter MARS6 to achieve similar performance to models many times larger. We show this in objective and subjective evaluations, comparing TTS output quality and reference speaker cloning ability.
Learn more here: https://camb-ai.github.io/mars6-turbo/