Text to speech · Chinese (Cantonese, Simplified)
Chinese (Cantonese, Simplified) text to speech for long-form narration
2 Chinese (Cantonese, Simplified) voices (1 female, 1 male) across the Natural lane.
Paste a full Chinese (Cantonese, Simplified) script, choose one voice, and NarrateHQ generates every section with that same voice and the same settings. When a line changes, regenerate only that section; the rest of the take is reused, and the timed SRT subtitles are rebuilt from the final audio.
How NarrateHQ splits Chinese (Cantonese, Simplified) scripts
Chinese (Cantonese, Simplified) scripts are split at fullwidth sentence punctuation such as 。！？, and a closing quote or bracket stays attached to the sentence it ends. When one sentence is too long for a single section, the cut moves to the nearest comma instead of an arbitrary character.
Every section is cut on whole characters, never inside a combined character or accent mark, and stays under the size limit a voice engine accepts in one request. That is what lets a long Chinese (Cantonese, Simplified) script run as one take instead of a series of manual pastes.
Chinese (Cantonese, Simplified) voice quality lanes
| Lane | Chinese (Cantonese, Simplified) voices | Credits per character |
|---|---|---|
| NaturalNatural and warm — the most popular choice for narration | 2 | 2 |
Every plan, Free included, draws on one Credits balance. See pricing for each plan's monthly Credits.
Chinese (Cantonese, Simplified) voices
-
XiaoMin
Bright, crisp and confident
-
YunSong
Deep, calm and formal
What every Chinese (Cantonese, Simplified) narration includes
- Timed SRT subtitles. Built from the same assembled audio you export, so captions line up with the final take.
- Section regeneration. Replace one section without paying to rebuild the whole script. How it works.
- Pronunciation dictionary. Fix a name or term once and every later generation reads it the same way. Read the guide.