Official BytePlus partnerBuilt on BytePlus, ByteDance's official AI platform
Text to speech · Japanese
Japanese text to speech with 3 AI voices
Paste a Japanese script, pick one of 3 preset voices (Mina (female), Shiori (female) and Haru (male)) and get natural speech in seconds. Set the speed, pitch and volume, write a two-speaker dialogue and download the clip.
- 3 Japanese voices
- Up to 5,000 characters per clip
- 1 credit per 1,000 characters
The 3 Japanese voices
Every voice under its real studio name, with its gender and use-case tags from the catalogue. Open it in Text to Speech and hear it read your own script.
What Japanese text to speech is good for
- Friendly greetings, shop announcements and social clips
- Narration for guides, tutorials and e-learning
- All-purpose voiceovers for product and app videos
Tips for Japanese scripts
- Write in normal Japanese script, kanji and kana, rather than romaji.
- Use 、 and 。 to place the pauses where you want them.
- Write names or rare words in kana when the kanji reading could be ambiguous.
Two-speaker dialogue
In "Two speakers" mode, cast Mina as Speaker A and Shiori as Speaker B and write up to 12 turns. Each turn is generated in its voice and the conversation plays back in order. You can also pair a Japanese voice with a voice in another language.
More Japanese audio tools
Speech to Text
Transcribe Japanese recordings into editable text, with auto-detect or the language picked.
Live Interpretation
Translate a voice clip into Japanese and hear the translation read by a built-in voice.
Audio Generation
Describe a scene in a prompt and the model performs it in Japanese, with cued lines and timing.
Voice Replication
Clone your own voice with your consent recorded and use it in Text to Speech next to the preset voices.
Pricing
Text to Speech costs 1 credit per 1,000 characters, with a minimum of 1 credit per clip: an 800-character Japanese script costs 1 credit and a full 5,000-character script costs 5 credits. The studio shows the cost before you generate, and failed clips are refunded automatically.
Japanese text to speech questions
How many Japanese voices are there?
3: Mina (female), Shiori (female) and Haru (male). Across all languages, Text to Speech has 45 voices in 14 languages.
Are there regional Japanese accents?
The catalogue does not label regional accents for the Japanese voices: they are listed as Japanese.
How much does it cost?
Text to Speech costs 1 credit per 1,000 characters, with a minimum of 1 credit per clip: an 800-character Japanese script costs 1 credit and a full 5,000-character script costs 5 credits. The studio shows the cost before you generate, and failed clips are refunded automatically.
Do the Japanese voices support emotions?
The Japanese voices have no emotion styles. Set the speed between 0.5x and 2x, the pitch and the volume to shape the read.
Can I transcribe or translate Japanese audio?
Yes, Speech to Text transcribes Japanese. Live Interpretation translates voice clips into Japanese.
Which platform does the audio studio run on?
Built on BytePlus, ByteDance's official AI platform. KreatorFlow is an official BytePlus partner; the audio studio and its credit prices are KreatorFlow's own.
Hear your Japanese script
Pick one of 3 voices, paste your text and generate. 1 credit per 1,000 characters.