Speaker Settings 🎧
The Speaker Settings section lets you manage speakers and control how their voices sound in a video or audio project. It helps you clean up audio, keep accents, and make the AI voice match the original speaker as closely as possible.
What are Personalized Speakers? 🧑🦱
Personalized speakers help AI dubbing sound natural. You give information about each person speaking. This helps the AI choose the best voice.
Why is Speaker Information Important? ❓
Missing speaker details can stop your AI translations. Always fill in this information.
Accurate details help the AI make good voices. This ensures smooth AI dubbing. Your videos will sound better.
How Do I Find Speaker Settings? ⚙️
Open your project.
Look for "Speaker settings."
Click on it to start.
It is usually in the top-right corner.
Accessing Speaker Information:
Head over to "Speaker settings" in the top-right corner and start inputting details for each speaker.
What Speaker Details Do I Need? 🎙️
You need to add some basic details for each speaker. This helps the AI dubbing process.
Name: Write the speaker's name.
For example, "John" or "Sarah."
Gender: Choose male or female.
Adding and Managing Speakers
At the top, you can add new speakers or switch between existing ones (Speaker 1, Speaker 2, etc.). Each speaker can have different voice settings.
You can also:
Rename the speaker
Select the speaker’s gender
Delete a speaker if needed
What is a Voice Model? 🗣️
A voice model tells the AI how to create the speaker's voice. There are two main ways.
What is "Voice From Original Video"? 🎤🎬
Voice From Original Video uses the speaker's voice from your current video. The AI learns from their words. It makes a new voice based on this.
What is "Voice Reference"? 🎧🔍
Voice Reference uses a voice you already have saved in your Voice Library. You can select any voice file from the library, and the AI will use it to clone the voice accurately.
We also provide a set of Default Voices, and you can create your own custom voices or upload your own recordings to use as voice references. You can clone a voice directly from the Voice Settings as well.
When you choose Clone & Save to Library for a particular speaker, the cloned voice is saved to your Voice Library, where you can name it and reuse it anytime.
Here is a helpful article on How to Select a Voice for Your Dubbing Project.
Audio Quality Controls
These options help improve voice quality. You can enable them using the toggle and click Confirm to apply. This can be turned on or off individually for each speaker.
Clean Reference:
This removes background noise from the original audio before processing.
Turn this on if the source audio has noise or disturbances.
Maintain Source Accent:
Keeps the speaker’s original accent while generating the AI voice.
Useful when you want the voice to sound natural and familiar.
Acoustic Quality Boost:
Reduces extra noise but may slightly affect how similar the AI voice sounds compared to the original.
What Is Voice Fine-Tuning Sliders?
These sliders help balance realism and clarity. These options are enabled by default. Use the slider to adjust and click Confirm to apply. Each speaker can be adjusted individually.
Stability
Controls how steady the voice sounds.
Higher values make the voice more consistent and less expressive.
Speaker Similarity
Adjusts how closely the AI voice matches the original speaker.
Higher values mean the voice sounds more like the original person.
Accent Boost
Strengthens the accent in the generated voice.
This is helpful when the accent feels too neutral or weak.
Voice Reference Selection
Select Voice References
You can choose voice references based on language.
For example:
English (United States): Voice from Original Media
Hindi (India): Voice from Original Media
This tells the system to use the original speaker’s voice style for each language.
Save the Voice
Once everything is set, you can clone and save the voice to the library for future use.
Ready to Start Your AI Dubbing Project? 🎬🚀
Now you know about personalized speakers. This helps your AI translations sound great. Setting up speakers correctly makes AI dubbing easy and effective.