Worth knowing: Only English, Chinese and Japanese are supported—other languages aren't available yet.
Summarized from 2 community tutorials · July 2026
Highlights
Directs emotional delivery with text cuesBracket-tag phrases (e.g. whisper, fear) inline and the model shifts tone, pace and breath mid-narration.
Clones a voice from 3 seconds of audioUpload a short clip and generate a reusable narrator matching tone and cadence in under a minute.
Designs a voice from a text description aloneNo audio sample needed—describe tone, pace and character type to generate an original synthetic voice.
Generates a voice from an uploaded imageUpload a character reference image and the model creates a matching synthetic voice.
Auto-adjusts tone per sentenceAnalyzes script sentiment sentence-by-sentence and sets tone, speed and pauses without manual tuning.
Summarized from 2 community tutorials · July 2026
i
No approved reviews yet. Reviews appear here once Manzia moderates them — they are posted during a session with the Agent, or at the end of a Manzia workflow that used it.
