Japanese AI Voice

Nanami — free Japanese text to speech

Nanami is a free female Japanese AI voice — a Microsoft neural voice. Type your text below to hear it read aloud, then download the audio. No account needed.

Female Global voice Free

Make Nanami say your words

Sample: “こんにちは、ようこそ!あなたの台本が本物のナレーションになったら、どんなふうに聞こえるか考えたことはありますか?この声は、物語やチュートリアル、商品紹介の動画を、落ち着いてはっきりと、または元気いっぱいに読み上げます。”

Voice details

Language
Japanese
Gender
Female
Type
Global · Microsoft neural
Download
MP3
Speed
Natural pace
Voice ID
ja-JP-NanamiNeural
Price
Free

3 free tries without an account, 10 generations a month with a free account, up to 5,000 characters each.

How Nanami sounds — measured

Median pitch

264 Hz

Intonation range

9.9 semitones

Tone (spectral centroid)

1,698 Hz

Speaking rate

5.9 characters/s

Pitch across the sample passage dashed line = Nanami’s median

How long your audio will be at 5.9 characters/s

1,000 characters
≈ 2 min 49 s
5,000 characters (free limit per render)
≈ 14 min
  • ↔Compared with Keita, Nanami has a higher pitch (264 vs 140 Hz) and slower delivery (5.9 vs 6.4 characters/s). Listen to Keita →

Measured by SpeakScribe in October 2026: Nanami reading the same sample sentence (“こんにちは!これが私の声です。”), the same text every Japanese voice reads at normal speed. Speaking rate and the pitch line come from the longer sample passage shown above, measured on 30 October 2026. How we measure, and every Japanese voice side by side → · Full methodology

About the Nanami voice

Nanami is a Global voice — a Microsoft neural voice served online — with natural intonation for its language and accent. Audio is exported as MP3. It is the only female Japanese voice on SpeakScribe.

Try this Japanese line

こんにちは!これが私の声です。

Writing Japanese scripts

Script tips for Japanese — numbers, punctuation and how this language is written — are collected on the Japanese voices page, together with a measured comparison of every Japanese voice.

Read the Japanese voice guide →

Nanami compared with other Japanese voices

VoiceGenderAccentTypePitch
Nanami (this voice)Female —Global 264 Hz
Keita Male— Global 140 Hz

Use Nanami in a conversation

With Multi-voice, Nanami can read one character while Keita (a male Japanese voice) reads another — the whole dialogue comes back as one MP3 with even volume between speakers. A free account can make 3 two-speaker dialogues a month; paid plans allow up to 4 speakers on Starter.

Try a dialogue with Nanami →

Formats, limits and help

Nanami: quick answers

Yes. The Nanami Japanese voice is free on SpeakScribe. Preview it instantly in your browser, then generate and download audio — no account required to start.
Measured from its audio, Nanami has a median pitch 264 Hz; intonation range 9.9 semitones; tone (spectral centroid) 1,698 Hz.
Global voices like Nanami speak at their natural pace; use punctuation and shorter sentences to slow the delivery.
Nanami exports MP3 audio, ready for YouTube, podcasts and most editing apps.