Shunya LabsShunya LabsPlayground

Radiance · Japanese

Japanese Text to Speech

Convert Japanese text into natural AI speech for voice agents, customer experiences, narration, applications, media, learning, and real-time conversational AI. Use Shunya Radiance to generate spoken Japanese from native Japanese text, with streaming and batch synthesis, expressive delivery, configurable speed, and production-ready audio formats.

99 global languages11 expression styles<350ms first audio7 audio formats

All Text-to-Speech Languages

Japanese · Conversational

こんにちは。ご注文の商品は明日の午前中に到着する予定です。

Hello. Your order is expected to arrive tomorrow morning.
Language · JapaneseExpression · ConversationalJapanese · Streaming<350ms first audio

Japanese TTS

Japanese Text in. Japanese Voice Out.

Japanese speech synthesis needs to do more than read characters aloud. Written Japanese combines multiple scripts, context-dependent readings, numbers, names, punctuation, English terminology, and different levels of conversational formality. Radiance includes Japanese in Shunya's extended world-language speech-synthesis coverage.

11

Languages on Radiance Oriental

11

Expression styles available across Radiance

<350ms

First-audio streaming latency

7

Supported audio output formats

Japanese is part of global TTS: Shunya's named 46-voice catalogue is centred on Indic languages and English. Japanese uses Radiance Oriental, which has its own native Japanese voices, Hina and Haruto.

CapabilityRadiance · Japanese Text to Speech
Native Japanese Text✓
Streaming Synthesis✓
Batch Synthesis✓
Expression Control✓
Speed Control✓
Multiple Audio Formats✓
Web Audio✓
Telephony Audio✓
API Integration✓
Voice Agent Integration✓
Cross-lingual Speech Platform✓

Try it yourself

Hear Japanese Using the Text Your
Application Actually Needs

Don't evaluate Japanese TTS only with a prepared sentence. Try a customer response, product name,address, notification, dialogue, instruction, narration, or Japanese-English sentence.

Japanese writing system

One Language. Multiple Scripts.

Japanese text commonly combines three writing systems inside the same sentence.

Kanji

漢字

Characters used extensively for nouns, verb roots, names, and many core concepts.

Hiragana

ひらがな

Used for grammatical endings, particles, native words, and other language functions.

Katakana

カタカナ

Frequently used for foreign words, brand terminology, technical vocabulary, and emphasis.

Example

新しいアプリをダウンロードしてください。

This single sentence contains:

  • Kanji: 新
  • Hiragana: しい / を / してください
  • Katakana: アプリ / ダウンロード
KanjiHiraganaKatakanaSpoken Japanese

A Japanese TTS workflow needs to process the complete sentence rather than treating each script as a separate language.

Context changes pronunciation

The Character Isn't Always Enough. Context Matters.

Japanese contains characters whose reading can depend on the word and surrounding context. Names, numbers, counters, abbreviations,and imported words introduce more variation. The goal is understandable Japanese speech - not character-by-character audio.

Kanji context

Readings that depend on the word and surrounding context.

Hiragana grammar

Particles, endings, and native grammatical structure.

Katakana vocabulary

Foreign words, brands, and technical terms.

Names

People, places, and companies with pronunciation variation.

Numbers

Counters, dates, and numeric expressions.

Dates & times

Calendar and clock expressions in running text.

Abbreviations

Short forms and imported acronyms.

Foreign terminology

English and Latin-script terms inside Japanese sentences.

Punctuation

Sentence boundaries and emphasis that shape delivery.

Text · CharactersLanguage processing · Interpret the sentenceSpeech · Generate the spoken form

Natural Japanese delivery

The Same Words Can Sound Very Different

Japanese speech changes according to context. A customer-service response should not necessarily sound like news narration. Radiance provides expression controls for changing the delivery of generated speech - 11 styles across the platform.

Neutral

General-purpose speech.

Conversational

Natural everyday interactions and voice agents.

Narrative

Long-form narration and storytelling.

News

Formal informational delivery.

Happy

Upbeat speech.

Sad

Softer, subdued delivery.

Enthusiastic

More energetic speech.

Angry

More intense speech.

Fearful

Anxious or tense delivery.

Same Japanese text: ご利用いただきありがとうございます。 - Neutral, Conversational, or Enthusiastic. The text remains the same. The delivery changes.

Japanese + English text

Real Japanese Doesn't Always Stay Japanese-Only

Japanese digital communication regularly contains English in product, software, and customer-facing content.

Brand namesTechnology termsProduct namesSoftware terminologyAcronymsInternational company names

Developer content

Shunya APIを使ってリアルタイム音声を生成できます。

Plan upgrade notice

Premiumプランへのupgradeが完了しました。

Support routing

Customer Supportチームにお問い合わせください。

Modern applications should expect Japanese text to contain Latin characters and English terminology.

Japanese + English termsOne TTS workflowContinuous speech

Mixed-script text should not require applications to manually create a separate audio file for every English term.

Real-time Japanese TTS

Generate Japanese While the AI is Responding

Pre-generated speech works for fixed announcements. Voice agents need dynamic speech.Radiance supports streaming synthesis through WebSocket connections.

<350ms

First-audio latency

LLM generates responseJapanese text becomes availableRadiance begins synthesisAudio chunks stream backUser hears the response

Stream instead of waiting - the complete paragraph does not need to finish generating before the speech pipeline begins producing audio.

Streaming

For conversations happening now

Use WebSocket TTS when speech needs to begin quickly.

Best for:

  • AI voice agents
  • Conversational assistants
  • Customer support
  • Interactive applications
  • Real-time translation experiences
  • Virtual assistants
  • Voice interfaces

Batch

For complete content

Generate a complete audio file from finished Japanese text.

Best for:

  • Narration
  • Notifications
  • Learning material
  • Media
  • Product demonstrations
  • Announcements
RequirementStreamingBatch
Voice agents✓-
Live conversation✓-
Complete audio file-✓
Narration✓✓
WebSocket✓-
HTTP-✓

Control the Japanese audio

Generate Speech for the Environment Where
It Will Actually Play

Different applications need different audio formats. Radiance supports seven output formats.

FormatBest for
PCMReal-time pipelines
WAVEditing and high-quality files
MP3Web and general delivery
OGG OpusWeb streaming
FLACArchival and lossless workflows
μ-lawPSTN / telephony
A-lawSIP and compatible telephony

Speaking speed

0.25× → 4.0×

Control speech speed for web, voice agents, and media workflows.

Trim silence

Remove unnecessary silence

Trim silence around generated audio where required.

One TTS API. Different delivery environments.

Japanese voices

Native Japanese Voices From Radiance Oriental

Japanese is synthesized with Radiance Oriental, Shunya's text-to-speech model for Asian languages.It includes two native Japanese voices, Hina and Haruto. Choose one by namein the voice field of any batch or streaming request.

2

Native Japanese voices: Hina and Haruto

Model

Radiance Oriental

Set the model value to radiance-oriental and the language value to ja.

Female voice

Hina

A native Japanese voice for voice agents, customer support, notifications, and narration.

Male voice

Haruto

A native Japanese voice for voice agents, announcements, product audio, and narration.

Choose a voice

Set the voice field

Pass Hina or Haruto as the voice value. The same voice works in batch and streaming requests.

Batch and streaming: Hina and Haruto work in HTTP batch and WebSocket streaming requests, with the same expression, speed, and output format controls.

Cross-lingual voice experience

One Voice Identity Across More Languages

Shunya's current public Radiance experience demonstrates a multilingual voice flow where thesame voice identity can move across languages - including English, Hindi, Japanese, Tamil,and Korean. The language changes. The intended voice identity remains consistent.

Voice sampleCreate voice identityChoose language · JapaneseGenerate speechSame voice experience
EnglishHindiJapanese
TamilKorean

Multilingual applications can use one recognisable voice experience across different markets. For production voice-cloning availability and configuration, use the capabilities enabled for the specific account or deployment.

Japanese voice agents

Give Conversational AI a Japanese Voice

Text-to-speech becomes particularly important inside voice-agent systems.

User speaks

注文状況を確認したいです。

Horizon

Converts speech into text.

LLM / Agent

Understands the request and generates a Japanese response.

Radiance

Generates spoken Japanese.

User hears

ご注文の商品は現在配送中です。

STT → LLM → TTS

Radiance becomes the speaking layer of the Japanese conversational experience.

Real-world use cases

Japanese TTS Wherever Software Needs to Speak Japanese

AI Voice Agents

Generate dynamic Japanese responses for conversational AI.

Customer Support

Provide spoken Japanese support experiences and automated responses.

Retail

Build Japanese-speaking kiosks, product assistants, and customer interfaces.

Travel & Hospitality

Generate spoken instructions and assistance for Japanese-speaking guests and travellers.

Notifications

Turn appointment updates, order messages, reminders, and alerts into Japanese speech.

E-learning

Generate Japanese audio for lessons, exercises, educational material, and pronunciation experiences.

Media

Create Japanese narration and speech for digital content.

Accessibility

Provide spoken alternatives to Japanese written interfaces.

Games & Interactive Experiences

Generate dynamic Japanese dialogue for supported applications.

Enterprise Applications

Add Japanese speech output to existing AI and business workflows.

Developers

Add Japanese Speech Generation to Your Application

Radiance provides HTTP batch and WebSocket streaming synthesis. Batch: POST https://ttsv2.shunyalabs.ai/v1/audio/speech · Streaming: wss://ttsv2.shunyalabs.ai/v1/realtime. Standard ISO language code: ja.

basic-request.json

{
  "model": "radiance-oriental",
  "language": "ja",
  "input": "<Conversational> こんにちは。今日はどのようなお手伝いができますか?",
  "voice": "Hina",
  "response_format": "mp3"
}

Basic workflow

Japanese text → Radiance → Japanese audio

Configure

Delivery options

LanguageAvailable voiceExpressionSpeedOutput formatSilence trimming

Japanese requests use Radiance Oriental: set model to radiance-oriental, language to ja, and voice to Hina or Haruto, the two native Japanese voices.

Explore the TTS API

Japanese for production

Beyond the Play Button

Generating one Japanese sentence is easy to demonstrate. Production speech systems need real-time synthesis, APIs, audio-formatcontrol, predictable latency, language handling, speech styles, telephony support, and deployment flexibility.

RequirementRadiance
Japanese Text to Speech✓
Japanese World-language Support✓
Native Japanese Text Input✓
Kanji / Kana Input✓
Batch Generation✓
Streaming Generation✓
First Audio<350ms
Expression Styles11
Speed Control0.25×-4.0×
Audio Formats7
MP3 / WAV✓
PCM / OGG Opus✓
FLAC✓
Telephony Formats✓
API Integration✓
LLM → TTS Workflow✓
Voice Agent Integration✓
Enterprise Deployment✓
Japanese textRadianceJapanese speechWebMobileVoice agentsTelephonyMediaAI applications

Questions

Frequently Asked Questions

What is Japanese Text to Speech?

Japanese Text to Speech converts written Japanese into spoken audio using speech-synthesis technology.

Does Shunya support Japanese Text to Speech?

Yes. Japanese is synthesized by Radiance Oriental, Shunya's text-to-speech model for Asian languages.

Is Japanese one of the 23 Indic TTS languages?

No. Japanese is synthesized by Radiance Oriental, not the Indic-language catalogue.

Can Shunya read Japanese script?

Japanese TTS is designed to synthesize Japanese text, including normal Japanese writing that combines Kanji, Hiragana, and Katakana.

Does Japanese have dedicated Shunya voice names?

Yes. Radiance Oriental includes two native Japanese voices: Hina (female) and Haruto (male). Choose one by passing its name as the voice value in a batch or streaming request.

Can Japanese TTS work in real time?

Yes. Radiance supports WebSocket streaming with first audio in under 350 ms.

Can Japanese TTS be used for voice agents?

Yes. Streaming TTS can provide the speech-generation layer of a Japanese conversational AI workflow.

Can I control the speaking style?

Radiance provides 11 expression styles, including Conversational, Narrative, News, Happy, Sad, Enthusiastic, and others.

Can I control Japanese speaking speed?

Yes. Radiance supports speed control from 0.25× to 4.0×.

Which audio formats are available?

Radiance supports PCM, WAV, MP3, OGG Opus, FLAC, μ-law, and A-law.

Can I use Japanese TTS for telephony?

Yes. Radiance supports μ-law and A-law output formats used in telephony environments.

Can Japanese text contain English terms?

Japanese frequently contains Latin-script brand names, acronyms, and foreign terminology. Mixed-script inputs should be tested using your own production sentences to confirm pronunciation quality.

Does Shunya support Japanese Speech to Text as well?

Yes. Japanese is also supported through Shunya's broader global speech-recognition coverage.

Does Parallax support Japanese?

No. Parallax, Shunya's translation model, covers Indian languages and does not include Japanese. Radiance speaks Japanese text, but it does not translate it.

Is Japanese TTS available through an API?

Yes. Radiance provides HTTP batch and WebSocket streaming APIs.

Get started

Turn Japanese Text into Speech

Don't judge Japanese TTS from our prepared sentence. Test yours. Try a customer response, Japanese name, product term,notification, narration, mixed Japanese-English sentence, voice-agent response, or text generated dynamicallyby your application. Hear how Shunya turns your Japanese text into speech.