Free Japanese AI Text to Speech with MP3 Download

Turn your Japanese text into natural, AI-generated speech for free: up to 1,000 characters a day, MP3 download, no account and no sign-up. Choose one of 39 AI voices – the language is detected automatically (57 languages supported) – and describe the tone, emotion or accent you want with voice instructions. The MP3 files may be used in commercial and non-commercial projects such as YouTube videos, presentations and e-learning.

Today's use: 0 / 1,000 characters

Voice update: the voices Alloy, Ash, Ballad, Coral, Echo, Fable, Nova, Onyx, Sage, Shimmer and Verse will be retired on December 31, 2026. We recommend switching to one of the new voices in the voice list (for example Kore, Charon, Puck or Zephyr): they follow voice instructions for tone, emotion and accent much better.

How to create Japanese AI speech as MP3

  1. Type or paste your text into the box above (up to 1,000 characters per day for free).
  2. Pick one of the 39 voices and, if you like, adjust the speed or switch on Add Instructions to describe the style.
  3. Click Read to listen or Download as MP3 to save the file.

The language is detected automatically from your text, so you do not need to select it.

Need more than 1,000 characters a day? Our AI premium plans start with a 24-hour pass.

Tips for voice instructions and pauses: AI voices overview.

Other languages

Afrikaans, Arabic, Armenian, Azerbaijani, Belarusian, Bosnian, Bulgarian, Catalan, Chinese, Croatian, Czech, Danish, Dutch, English, Estonian, Finnish, French, Galician, German, Greek, Hebrew, Hindi, Hungarian, Icelandic, Indonesian, Italian, Kannada, Kazakh, Korean, Latvian, Lithuanian, Macedonian, Malay, Maori, Marathi, Nepali, Norwegian, Persian, Polish, Portuguese, Romanian, Russian, Serbian, Slovak, Slovenian, Spanish, Swahili, Swedish, Tagalog, Tamil, Thai, Turkish, Ukrainian, Urdu, Vietnamese, Welsh.

Example audio files for all voices in Japanese

Example sentence: 素早い茶色のきつねが怠け者の犬を飛び越える。

Voice instructions with the new voices

Same sentence, different instructions: 古い時計が真夜中の十二時を打ち、家のどこかで扉がゆっくりと開いた。誰も動かなかった。

Kore no instruction
Kore “Whisper the whole text”
Charon “Speak with an Osaka accent, lively and playful”
Puck “Sound very excited and energetic”
Sulafat “Read with a calm and soothing tone”
Algenib “Speak in a dramatic and theatrical tone”

New voices

Achernar female, soft
Achird male, friendly
Algenib male, gravelly
Algieba male, smooth
Alnilam male, firm
Aoede female, breezy
Autonoe female, bright
Callirrhoe female, easy-going
Charon male, informative
Despina female, smooth
Enceladus male, breathy
Erinome female, clear
Fenrir male, excitable
Gacrux female, mature
Iapetus male, clear
Kore female, firm
Laomedeia female, upbeat
Leda female, youthful
Orus male, firm
Puck male, upbeat
Pulcherrima female, forward
Rasalgethi male, informative
Sadachbia male, lively
Sadaltager male, knowledgeable
Schedar male, even
Sulafat female, warm
Umbriel male, easy-going
Vindemiatrix female, gentle
Zephyr female, bright
Zubenelgenubi male, casual

Current voices (available until December 31, 2026)

Alloy female
Ash male
Coral female, deeper voice
Echo male
Fable female
Onyx male, deeper voice
Nova female, soft
Sage female
Shimmer female

Facts about the Japanese language:

Always interesting and ever evolving in the modern era, the Japanese language is spoken by roughly 130 million people worldwide. While it has been said that Chinese has had an influence on the origins of Japanese, there is a great deal of debate about its exact history. Most linguists do agree that its origins likely come from Turkish, Korean, and Mongolian.

Written Japanese falls into three major categories:

Hiragana: The most basic form of the Japanese language, each syllable in Hiragana is represented by a character in a phonetic system of which there are 46.

Katakana: Also represented by a character for each syllable, the 48 characters in the Katakana chart are primarily for foreign words used in Japanese.

Kanji: The multi-syllabic and most complex of the characters, there are roughly 2,000 Kanji. Japanese children do not learn Kanji until grade school and continue throughout high school.

A lesser included fourth category, Romaji is the "Romanized" version of Japanese. Instead of unique characters, symbols are represented in the Latin A-Z alphabet and sounds are written phonetically.

While written Japanese may prove quite arduous, spoken Japanese and grammar is very simple. There are varying levels of politeness, but Japanese has much fewer verb conjugations than other languages, uses no particles, and the subject is oftentimes omitted.

Throughout Japan there are many dialects by region, referred to as "ben" or "go" that vary widely by prefecture.

Japanese truly is as fascinating as it is a challenge.

Frequently asked questions

Are the AI voices free?

Yes. You can convert up to 1,000 characters per day with the AI voices for free and download the result as MP3, without an account.

Which AI voices are available?

39 natural AI voices: 30 new voices such as Kore, Charon, Puck, Zephyr, Leda and Sulafat, which follow voice instructions for tone, emotion and accent especially well, and the voices Alloy, Ash, Coral, Echo, Fable, Onyx, Nova, Sage and Shimmer until December 31, 2026. The language (57 supported) is detected automatically from your text.

Can I control the style of the voice?

Yes. With voice instructions you describe tone, emotion, accent or a character, for example "speak in a calm, warm tone". You can also change the speed and add pauses with <break time="2s"/>.

Can I use AI voice MP3s commercially?

Yes, in commercial and non-commercial projects such as YouTube videos, podcasts, presentations, e-learning and apps.

Does it work in my language?

The AI voices detect the language of your text automatically and support 57 languages, for example English, Spanish, Portuguese, French, German, Vietnamese, Indonesian and Arabic.

More questions and answers in our FAQ

ConvertSpeech Need the opposite — Speech to Text?
Upload any audio or video and get an accurate transcript in minutes.
Free to try on our sister site ConvertSpeech.com →

Current Limit: ~125 words or 1,000 characters / day | Powered by OpenAI and Google Gemini Text-To-Speech