Shunya LabsShunya LabsPlayground

Horizon · Radiance

Japanese AI Voice Agent

Build AI voice agents that can listen to Japanese, understand customer requests in real time, and respond through natural Japanese speech across web, mobile, and telephony experiences.

Use Shunya Horizon and Radiance as the speech layer for Japanese customer support, order tracking, retail, travel, notifications, enterprise applications, and conversational AI - with streaming transcription, native Japanese text input, expressive TTS, telephony audio, speaker-aware transcripts, and post-call intelligence.

Horizon streaming transcriptionRadiance Japanese speech<350 ms first audioja language code
User

注文状況を確認したいです。

AI Agent

承知しました。注文番号を教えていただけますか?

Japanese speech · Horizon and Radiance
Customer supportOrder trackingTelephonyKanji / Kana

Japanese AI Voice Agent

From spoken Japanese to an AI responseand back to Speech

A Japanese-speaking user may ask:

  • 注文状況を確認したいです。

The application needs to:

  • Understand the spoken Japanese.
  • Convert it into text.
  • Process the request.
  • Generate an appropriate Japanese response.
  • Turn that response back into speech.
User speaks JapaneseHorizonJapanese speech becomes textLLM / AI / applicationUnderstand request. Retrieve information. Apply business logic. Generate Japanese response.RadianceJapanese text becomes speechUser hears response

Shunya supports this voice-agent architecture for Japanese speech workflows.

CapabilityJapanese voice agent
Japanese Speech Recognition
Real-time Streaming STT
Japanese Text to Speech
Native Japanese Text Input
Kanji / Kana Input
Streaming TTS
Batch TTS
Expression Control
Speed Control
Telephony Audio
Speaker Diarization
Speaker Identification
Word-level Timestamps
Intent Detection
Sentiment Analysis
Summarisation
API Integration

Try a Japanese voice conversation

Test the Japanese your usersActually Speak

Example

User

注文状況を確認したいです。

AI Agent

承知しました。注文番号を教えていただけますか?

User

48217です。

Japanese speechHorizonTranscriptOrder applicationJapanese response textRadianceSpoken Japanese response

Another customer may ask:

  • 予約を変更したいです。
  • 支払いの確認がまだ届いていません。

Japanese speech to text

Turn spoken Japanese intomachine-readable Text

Japanese speech can appear in:

  • Customer calls
  • Voice agents
  • Meetings
  • Interviews
  • Support conversations
  • Mobile applications
  • Telephony
  • Interactive AI

Japanese is included in Shunya's broader global speech-recognition coverage.

User speaks注文はいつ届きますか?HorizonTranscript注文はいつ届きますか?ApplicationOrder-status workflow

The transcript becomes the application input.

Real-time Japanese STT

Understand the user while theyare still Speaking

Voice agents need transcription during the conversation. Shunya's speechstack supports WebSocket streaming for live voice recognition.

User speaks明日の予約を...Partial transcript明日の予約を...User continues...金曜日に変更したいです。Final transcript明日の予約を金曜日に変更したいです。ApplicationRescheduling workflow

Use real-time STT for

  • Japanese voice agents
  • Customer support
  • Agent assist
  • Interactive assistants
  • Live call routing
  • Conversational applications

The application does not need to wait until the call ends before using the transcript.

Japanese writing system

Japanese uses several scriptsin the same Language

Normal Japanese text combines:

Kanji

漢字

Used extensively for names, concepts, nouns, and verb roots.

Hiragana

ひらがな

Used for grammatical forms, particles, and native words.

Katakana

カタカナ

Frequently used for foreign words, brands, technology, and imported terminology.

A Japanese AI voice application needs to work with real Japanese text rather than treating the language as one simple script. Shunya supports native Japanese text input including Kanji and Kana for Radiance.

Japanese + English terms

Real Japanese digital conversations containEnglish Vocabulary

Japanese customer experiences frequently include:

  • Brand names
  • APIs
  • Product names
  • Software terminology
  • Acronyms
  • International company names

Example

Shunya API を使ってリアルタイム音声を生成できます。

Another

Premium プランへの upgrade が完了しました。

Shunya supports Japanese text containing English and Latin-script terms.

Japanese + English termsRadianceContinuous speech

Production applications should test the actual brand names and foreign terminology they expect users to hear.

Radiance for Japanese

Generate spoken Japanese fromapplication Text

Radiance includes Japanese within Shunya's extended world-language speech-synthesis coverage.

Japanese textこんにちは。今日はどのようなお手伝いができますか?RadianceJapanese audio

This generated speech can be used in:

  • AI voice agents
  • Customer support
  • Retail applications
  • Travel applications
  • Notifications
  • Mobile apps
  • Web applications
  • Telephony
  • Enterprise software

Streaming Japanese TTS

Start speaking before the full response isComplete

A prerecorded Japanese announcement can wait. A conversational AI agent cannot.Radiance supports Japanese streaming synthesis over WebSocket.

<350 msFirst-audio latency supported for Japanese streaming TTS.

LLM generates Japanese textRadiance begins synthesisAudio chunks stream backUser begins hearing response

Streaming is suited to

  • Japanese voice agents
  • Customer support
  • Virtual assistants
  • Real-time information services
  • Interactive applications
  • Voice interfaces

Japanese TTS voice availability

Use the Japanese voices yourdeployment Exposes

Radiance Indic publishes 46 named voices across Indic languages and English. Japanese uses the world-language synthesis path instead.

World languages such as Japanese use the built-in speaker exposed by your Radiance deployment rather than a published dedicated Japanese male/female pair in the Indic voice catalogue.

Capabilities to validate

  • 46 Japanese voices
  • Dozens of native Japanese voices
  • Japanese male voice X
  • Japanese female voice Y

unless your deployment exposes them.

Supported position

  • Japanese synthesis is supported.
  • Streaming and batch TTS are supported.
  • Use the voice exposed by the active Shunya deployment.

Control Japanese speech style

The same Japanese sentence can be deliveredDifferently

Radiance documents 11 expression styles. Examples include:

  • Conversational
  • Narrative
  • News
  • Happy
  • Sad
  • Enthusiastic
  • Neutral

Customer support

Conversational

Announcement

News or neutral

Media / learning

Narrative

The application can select an appropriate style according to the experience.

Control Japanese speaking speed

Adjust how quicklythe agent Speaks

Radiance supports speed control from 0.25× to 4.0×.

Slower

Instructions, accessibility, and learning content.

Normal

Everyday conversation.

Faster

Concise information workflows.

The application can configure speech speed without changing the underlying response text.

Japanese audio formats

Generate speech for the actual playbackEnvironment

Radiance documents seven output formats: PCM, WAV, MP3, OGG Opus, FLAC, μ-law, and A-law.

Real-time pipelines

  • PCM

Web

  • MP3
  • OGG Opus

High-quality audio

  • WAV
  • FLAC

Telephony

  • μ-law
  • A-law

One Japanese TTS platform can serve multiple delivery channels.

Japanese telephony

Voice AI should work beyonda Browser

A Japanese-speaking customer may interact through:

  • PSTN
  • SIP
  • Contact-center systems
  • IVR
  • Mobile calling workflows
Phone callJapanese speechHorizonAI / applicationRadianceJapanese caller

Generated Japanese TTS supports μ-law and A-law formats for telephone-oriented output.

Customer support

Provide spokenJapanese Support

A customer might ask:

  • 注文はいつ届きますか?
  • 支払いの確認がまだ届いていません。
  • 担当者と話したいです。
CustomerHorizonSupport applicationBusiness systemJapanese responseRadiance

Shunya handles speech. The support system handles the customer issue.

Order tracking

Let customers ask for shipmentstatus in Japanese

  • 注文状況を確認したいです。
UserHorizonOrder tracking requestOrder-management systemCurrent order informationJapanese responseRadiance

The commerce system remains the source of truth for the actual shipment status.

Appointment workflows

Handle booking and reschedulingConversations

  • 予約をしたいです。
  • 明日の予約を変更したいです。
Japanese requestHorizonAppointment applicationScheduling systemJapanese responseRadiance

The scheduling system remains responsible for actual availability and appointment changes.

Retail

Add Japanese voice to digital andphysical Retail

Retail is a supported Japanese TTS use case.

Possible experiences include:

  • Product assistants
  • Store kiosks
  • Customer-service interfaces
  • Order information
  • Interactive product guidance
UserJapanese speechHorizonRetail applicationJapanese responseRadiance

Travel and hospitality

Serve Japanese-speaking gueststhrough Voice

Travel and hospitality are supported Japanese TTS use cases.

Voice applications may support:

  • General service questions
  • Booking information
  • Instructions
  • Hospitality assistance
  • Travel information

The connected travel or hospitality application remains responsible for business data and actions.

Notifications

Turn dynamic application messages intoJapanese Speech

Radiance can generate Japanese audio for:

  • Appointment updates
  • Order messages
  • Reminders
  • Alerts
  • Service information

Notifications are a supported Japanese TTS use case.

Application eventJapanese textRadianceSpoken notification

The notification can be pre-generated or produced dynamically depending on the workflow.

Enterprise applications

Add Japanese voice without rebuildingcore business Logic

The same enterprise application may support:

  • English
  • Japanese
  • Korean
  • French
  • Spanish
  • and other supported languages
Business applicationJapanese response textRadianceJapanese speech

Japanese becomes another voice interface around the existing software rather than a separate product architecture.

Human handoff

Some conversations stillneed a Person

The application may transfer the interaction when:

  • User asks for a human
  • Request is unsupported
  • Business rules require manual review
  • Information is unavailable
  • A specialist is needed
Japanese AI agentCan supported workflow continue?YesContinueNoHuman agent / specialist

The surrounding application controls escalation.

Speaker diarization

Preserve who said what inrecorded Japanese Calls

If a customer and human support agent speak in the same call, speaker diarizationcan separate the participants.

With diarization

SPEAKER_00 注文状況を確認したいです。
SPEAKER_01 注文番号を教えていただけますか?
SPEAKER_00 48217です。

Speaker-aware transcripts support:

  • QA
  • Search
  • Training
  • Call review
  • Summaries
  • Analytics

Speaker identification

Resolve registered internal speakersWhere Configured

Speaker diarization separates voices. Speaker identification can matchregistered speaker profiles where configured.

Before

SPEAKER_01

確認します。

After

Agent A

確認します。

Unknown customers can remain anonymous labels.

Word-level timestamps

Connect transcript text backto Japanese Audio

Verbose transcription can include, for individual words:

  • Start time
  • End time
  • Confidence

Use for

  • Call review
  • Search
  • Playback
  • QA
  • Training
  • Transcript indexing

The timestamp layer makes a completed Japanese transcript more useful than plain text alone.

Post-call intelligence

Turn completed Japanese conversations intostructured Information

Shunya's broader STT workflow documents batch intelligence fields including:

  • Intent
  • Sentiment
  • Emotion
  • Summary
  • Speaker diarization
  • Speaker identification
  • Word timestamps
  • Redaction
Recorded Japanese callHorizonTranscriptOptional intelligenceCRM / QA / Search / Analytics

These enrichments should be positioned as post-call/batch capabilities rather than automatically live during every agent turn.

Intent

Understand what the user wastrying to Accomplish

An organisation may define intents such as:

  • Order status
  • Appointment request
  • Support
  • Payment question
  • Product enquiry
  • Human-agent request
CallJapanese transcriptIntentDownstream workflow / analytics

The organisation defines the taxonomy.

Sentiment and emotion

Add context afterthe Interaction

A customer may say:

何度も問い合わせています。

The transcript contains the actual statement. Batch intelligence can add:

Sentiment

  • Positive
  • Neutral
  • Negative

Emotion

Dominant emotion associated with transcript segments.

Potential uses include:

  • QA
  • Customer-experience analysis
  • Escalation review
  • Training

These signals should complement the transcript rather than replace explicit customer meaning.

Call summaries

Reduce a long Japanese conversation into ashorter Record

A completed call may contain:

  • Reason for contact
  • Customer question
  • Information provided
  • Action taken
  • Escalation
  • Next step
Complete callJapanese transcriptSummaryCRM / support / analytics

Shunya's broader batch intelligence layer documents summarisation.

Japanese voice cloning and cross-lingual experience

One voice identity across languagesWhere Enabled

Shunya's public Radiance experience demonstrates a cross-lingual voice flow including Japanese.

Voice sampleCreate voice identityChoose languageJapaneseGenerate speechConsistent voice experience

ImportantFor production voice-cloning availability and configuration, use the capabilities enabled for the specific Shunya account or deployment. Do not assume every deployment exposes the same cloned-voice configuration.

Japanese is not translation

Speech recognition and speech synthesisare different from Translation

Speech recognition, speech synthesis, and translation are separate capabilities in the Shunya product family.

Japanese Speech to Text

Supported.

Japanese Text to Speech

Supported.

Parallax Translate for Japanese

Enable when your deployment exposes the Japanese translation pairs you need.

Japanese speechHorizonJapanese textLLM / applicationJapanese response textRadiance

Cross-language translation through Parallax is separate from Japanese STT and TTS:

  • English → Japanese translation through Parallax
  • Japanese → English translation through Parallax

Japanese voice AI does not require translation when the interaction remains Japanese end to end.

Japanese + global voice AI

Japanese can sit inside a larger multilingualPlatform

Shunya's Japanese TTS material places Japanese alongside supported world languages such as:

  • Korean
  • Chinese
  • French
  • German
  • Spanish
  • Arabic
  • Russian
  • Thai
  • Vietnamese
  • and others
One applicationEnglish users · Japanese users · Korean users · Spanish usersShunya speech stackAI / application

The language changes. The underlying business application does not need to be completely rebuilt.

Developers

Build a complete Japaneseconversational Pipeline

InputJapanese speechHorizonGlobal speech-recognition routeJapanese transcriptAI / LLM / applicationConversation context, knowledge retrieval, business rules, and actionsJapanese response textRadianceLanguage: jaOutputJapanese speech

Batch

HTTP synthesis

Streaming

WebSocket synthesis

The existing Japanese TTS developer material documents batch HTTP synthesis, streaming WebSocket synthesis, and language code ja.

TTS configuration. Choose:

  • Language
  • Available voice
  • Expression
  • Speed
  • Output format
  • Silence trimming

Important voice noteDo not hard-code an invented Japanese voice name. Use the voices available in the active Shunya deployment.

Real-world Japanese voice agent use cases

Japanese voice wherever software needsConversation

Customer Support

Provide spoken Japanese customer-service interactions.

Order Tracking

Understand shipment questions and return order information through connected systems.

Retail

Build Japanese-speaking kiosks and product assistants.

Travel & Hospitality

Provide Japanese voice assistance and information.

Appointment Workflows

Handle booking and scheduling conversations through connected applications.

Notifications

Generate spoken reminders, updates, and alerts.

Enterprise Applications

Add Japanese voice to existing business systems.

Interactive AI

Create Japanese conversational assistants.

Accessibility

Provide spoken alternatives to written Japanese interfaces.

Games & Interactive Experiences

Generate dynamic Japanese dialogue where appropriate.

These use cases are consistent with the Japanese TTS applications Shunya supports for production voice AI.

Built for production Japanese voice AI

Beyond one Japanesedemo Sentence

A production Japanese AI Voice Agent may need:

  • Japanese STT
  • Real-time streaming recognition
  • Native Japanese text
  • Kanji / Kana handling
  • Japanese TTS
  • Streaming synthesis
  • Expression control
  • Speed control
  • Telephony audio
  • English terms inside Japanese text
  • Speaker diarization
  • Word timestamps
  • Post-call intelligence
  • API integration
  • Human handoff
  • Deployment-aware voice selection
RequirementShunya Japanese stack
Japanese STT
Streaming STT
Japanese TTS
Native Japanese Input
Kanji / Kana
Streaming TTS
Batch TTS
First Audio <350 ms target
Expression Styles11
Speed Control0.25×–4.0×
Audio Formats7
Telephony Output
Speaker Diarization
Speaker Identification
Word Timestamps
Intent
Sentiment
Summarisation
API Integration
Japanese userHorizonAI / applicationRadianceJapanese response

One end-to-end Japanese conversational experience.

Questions

Frequently Asked Questions

What is a Japanese AI Voice Agent?

A Japanese AI Voice Agent is a conversational application that understands spoken Japanese, processes the request through an AI or business application, and returns spoken Japanese.

Does Shunya support Japanese Speech to Text?

Yes. Japanese is included in Shunya's global speech-recognition coverage.

Can Japanese STT work in real time?

Yes. Shunya's broader Horizon platform supports WebSocket streaming for live voice-agent workflows.

Does Shunya support Japanese Text to Speech?

Yes. Japanese is included in Radiance world-language synthesis coverage.

What language code should I use for Japanese TTS?

Use the standard Japanese language code ja in Radiance requests.

Can Radiance read Kanji?

Japanese TTS supports native Japanese text, including normal Japanese writing using Kanji and Kana.

Does Japanese have dedicated Shunya male and female voice names?

Radiance Indic publishes named voices for Indic languages and English. Japanese uses the world-language synthesis path rather than a dedicated Japanese male/female voice pair in that catalogue.

Can Japanese TTS stream in real time?

Yes. Streaming Japanese TTS is supported over WebSocket.

What is the supported first-audio latency?

Japanese streaming TTS documents first audio in under 350 ms.

Can I change Japanese speaking speed?

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

Can I change the expression?

Yes. Radiance documents 11 expression styles.

Which audio formats are available?

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

Can Japanese TTS work with telephony?

Yes. μ-law and A-law output formats are supported for telephony environments.

Can Japanese text contain English brand or product names?

Yes. Japanese application text may include Latin characters and English terminology. Test pronunciation with the text your users actually speak and type.

Can customer and agent speech be separated?

Yes. Shunya's broader automated speech recognition platform supports speaker diarization.

Can known speakers be identified?

Registered speaker profiles can be combined with speaker identification where configured.

Can Japanese calls include word-level timestamps?

Yes. The broader Horizon structured-output workflow supports word-level timing.

Can completed Japanese calls be summarised?

Yes. Summarisation is part of Shunya's supported batch intelligence layer.

Can intent and sentiment be analysed?

Yes. Intent, sentiment, emotion, and related enrichment are available in supported batch STT workflows.

Can I use a Japanese AI Voice Agent for customer support?

Yes. Japanese customer support is a supported Radiance use case.

Can it support retail?

Yes. Retail is a supported Japanese TTS use case.

Can it support travel and hospitality?

Yes. Travel and hospitality are supported use cases.

Can it support order tracking?

Yes. Order-status conversations appear in the Japanese voice-agent examples.

Does Parallax Translate support Japanese?

No. Parallax's supported language set does not list Japanese, so English↔Japanese translation through Parallax should not be assumed.

Can I therefore build English-to-Japanese translation into this voice agent?

Japanese automated speech recognition and speech synthesis are supported end to end in Japanese. Add Parallax translation only when your deployment exposes the language pair you need.

Can Japanese be part of a multilingual voice application?

Yes. Japanese fits into Shunya's broader global speech platform alongside other languages.

Get started

Build conversational AI thatspeaks Japanese

Let Japanese users speak naturally. Use Horizon to turn spoken Japanese into machine-readable text. Use your AI or business applicationto understand and act. Use Radiance to respond through natural Japanese speech. Test customer support, order tracking, retail,travel, notifications, Japanese-English terminology, telephone audio, and the real conversations your users actually have.