Text Voiceover

Text Voiceover

Text Voiceover converts input text or text extracted from uploaded documents into voiceover audio. It is suitable for course narration, ad voiceover, podcast segments, and audio content production.

Steps

1. Open Text Voiceover.
2. Enter or paste text, or upload a document to extract text.
3. Choose whether to translate the text first.
4. Select or confirm a voice.
5. Review the estimated credit cost and submit the project.
6. Wait for system processing to complete.
7. Open the editor to view and edit text or subtitle content.
8. Export audio.

Input methods

Text Voiceover supports direct text entry and uploaded TXT, PDF, SRT, and other documents that can be parsed into voiceover copy.

Uploaded files are only the input source. The project runs based on the parsed text. If a PDF is a scanned image, text may not be extracted. SRT files extract subtitle text as voiceover copy.

Dubbing rules

In Text Voiceover, dubbing is required. You must select or confirm an available voice before submitting the project.

Available voices include:

Each selectable voice supports preview.

• Voxsail standard voices.
• Third-party shared voices.
• Completed cloned voices.

Voiceover after translation

You can translate the text first and then generate voiceover from the translated text. When translation is selected, you must choose the original language and target language, and they cannot be the same.