Languages
- English
- Hindi
- Tamil
- Telugu
- Bengali
- Marathi
- Spanish
- French
- Japanese
- Korean
- Other supported languages
Horizon · Radiance
Build AI voice agents that can listen, understand, and respond across multiple languages without rebuilding the entire voice stack for every market.
Use Shunya Horizon and Radiance as the speech layer for multilingual conversational AI - with global speech recognition, Indian-language models, code-switched conversations, automatic language detection, streaming transcription, and multilingual speech synthesis.
Can you check the status of my order?
मेरा order कब deliver होगा?
Same application · different speech pathMultilingual AI Voice Agent
A global voice application may need to handle customers who speak:
Languages
The challenge is not only translating a user interface. The application needs to listen to real speech.
That speech may include
A Multilingual AI Voice Agent can use one conversational architecture while selecting the speech-recognition and speech-synthesis path that fits the actual conversation.
| Capability | Shunya speech stack |
|---|---|
| Global Speech Recognition | |
| Indian-language Recognition | |
| Automatic Language Detection | |
| Code-switched Recognition | |
| Real-time Streaming STT | |
| Batch STT | |
| Multilingual TTS | |
| Streaming TTS | |
| Batch TTS | |
| Cross-lingual Synthesis | |
| Mixed-language TTS | |
| Speaker Diarization | |
| Word-level Timestamps | |
| Telephony Audio | |
| API Integration |
Try a multilingual conversation
A multilingual voice agent should not be judged only on one prepared English sentence. Test realistic customer interactions.
Can you check the status of my order?
मेरा order कब deliver होगा?
Quiero saber cuándo llegará mi pedido.
Mera payment complete hai but confirmation अभी तक नहीं आया.
These conversations may need different speech-recognition paths while still entering the same business application.
Global speech recognition
Horizon Universal is Shunya's model for broad global speech recognition. The supported languages include:
Global languages
The same speech-recognition architecture can support multiple international markets rather than requiring an entirely separate ASR stack for each language.
Indian-language voice agents
India requires more than English-only speech recognition. Horizon Indic is designed around Indian languages and Indian speech patterns.
Indian languages
A user should not have to switch to English simply because the software was not designed for regional speech.
Automatic language detection
A caller may begin speaking immediately. Horizon supports automatic language detection when a language is not explicitly locked.
This can support experiences where the user does not first select Press 1 for English or Press 2 for Hindi. When the language is known, the application can explicitly provide the language code. Locking a known language can reduce ambiguity, particularly for short audio where less speech context is available.
Useful when language is unknown.
Useful when the application already knows the expected language.
Code-switched conversations
A customer may start in Hindi and switch to English inside the same sentence.
मेरा payment complete है but confirmation अभी तक नहीं आया.
என் order இன்னும் deliver ஆகல.
These are not two separate conversations.
Horizon Code-Switch is designed for conversations that naturally switch languages inside the same sentence or interaction.
Hinglish voice agent
Hinglish is common in:
Mera order कब deliver होगा?
Payment successful show ho raha hai but confirmation नहीं आया.
Kal ka appointment reschedule karna hai.
A voice agent should let the user speak naturally rather than forcing language purity.
Regional language + English
Business and digital terminology often remains English even inside regional-language speech.
என் appointment tomorrow morning confirm ஆகிவிட்டதா?
నా payment successful అయింది but confirmation రాలేదు.
আমার order dispatch হয়েছে?
माझी appointment reschedule करायची आहे.
The user should not need to manually switch recognition models every time the vocabulary changes.
Choose the model that matches the conversation
The Horizon family includes different recognition paths.
For broad international-language speech. Best suited to supported global-language conversations.
For Indian-language speech and regional conversational patterns.
For conversations where supported languages naturally mix.
For specialised healthcare speech where the supported medical workflow is appropriate.
The application should choose the model according to the actual audio instead of treating multilingual speech as one generic category.
One application, multiple languages
The same customer-support workflow may need to work for several customers.
English
Hindi
Spanish
Tamil-English
The business task may be identical: check order status.
This separation allows language expansion without rebuilding the business workflow from scratch.
Multilingual text to speech
Listening is only half of a voice agent. The application must also speak. Radiance is designed as a multilingualspeech platform rather than an English-only voice generator. The supported catalogue coversEnglish, major Indian languages, and extended world-language synthesis.
Possible experiences
The exact voices available come from the current deployment, not from a generic language list.
Cross-lingual synthesis
Radiance documents cross-lingual synthesis. This allows supported voice workflowsto extend across languages without replacing the speech platform.
The exact voice behaviour and available speaker identities depend on the current service configuration. Not every language has its own named voices.
Mixed-language TTS
Multilingual conversations do not only affect recognition. The response may itself mix languages. Radiance documentsmixed-language synthesis for Hindi and English and is positioned for multilingual conversational speech.
आपका appointment tomorrow morning confirm है.
This can produce a more natural conversational experience than splitting every phrase into separate speech engines.
Streaming STT
Voice agents need live transcription. Horizon provides real-time streaming recognition.
Streaming is suited to
The agent does not have to wait until the entire recording is complete.
Streaming TTS
Conversational AI should not wait for an entire audio file before playback begins. Radiance supports streamingsynthesis, with a supported first-audio expectation under 350 ms for relevant workflows.
Streaming TTS is suited to
The result is a conversational pipeline rather than a batch audio-generation workflow.
Complete multilingual voice loop
This basic architecture remains consistent across multilingual experiences.
Language preference
A customer profile may contain a preferred language. The application can use that context.
Configure a Hindi-first speech workflow.
The same application can use another speech path.
The language preference itself belongs to the customer or business system.
Change language during the conversation
A multilingual application can use that request to change the configured speech path where supported.
Can we continue in Hindi?
The underlying business workflow does not need to restart.
Language detection vs Code-Switch
Automatic language detection answers which language is being spoken. Code-Switch recognition answerswhat happens when more than one language appears naturally in the same conversation.
Primarily one language. Detect the language, then transcribe.
Multiple languages mixed. Use the Code-Switch model for a continuous transcript.
Applications should not treat these as identical features.
Real-world multilingual audio
A production voice agent also needs to handle:
A clean studio recording cannot represent all of these conditions. Production testing should include the audio users actually produce.
Telephony audio
A multilingual voice experience must work beyond a browser microphone. Horizon supports telephony-oriented streaming audio.
Documented call audio
The language layer and telephony layer need to work together.
TTS audio formats
Radiance supports PCM, WAV, MP3, OGG Opus, FLAC, μ-law, and A-law.
Web
High-quality audio
Telephony
This allows multilingual generated speech to fit web, mobile, media, and telephone applications.
Speaking speed and expression
Radiance documents speech controls including speed from 0.25× to 4.0× and 11 expression styles for relevant workflows.
A voice agent may need different speaking behaviour for
The application can configure the speech output according to the experience it is building.
Speaker diarization
A recorded multilingual customer call may include two or more people. Speaker diarization can separate transcript segments according to speaker.
I need to change my booking.
Sure. Which date works for you?
Use for
This remains useful regardless of the language being spoken.
Word-level timestamps
Verbose transcription can include:
Use for
The same structured transcription workflow can support multilingual recordings.
Post-call intelligence
For supported batch workflows, Shunya supports optional fields such as:
These enrichments are batch capabilities: they run on the completed call, not live on every voice-agent turn.
Customer support
A support voice agent can use the same application logic across different language experiences.
Where is my order?
मेरा order कहाँ है?
Mera order dispatch ho gaya hai kya?
The workflow remains customer support. Only the speech path changes.
Sales
A prospect may explain the same requirement in English, Hindi, or a mixed-language conversation.
We need transcription for our customer-support team.
Sales logic does not have to be tied to a single spoken language.
Appointment booking
A user may ask for the same appointment in more than one way.
I need an appointment Friday morning.
Friday morning appointment chahiye.
The scheduling system remains the source of truth. The speech layer adapts to the conversation.
Banking and financial services
Customers may discuss account actions using a mixture of local-language and English financial terminology.
Customers may discuss
The speech platform handles the language. The financial system handles the account action.
Healthcare
Shunya separately documents Horizon Medical for healthcare-oriented speech recognition.
A healthcare voice application may need
Universal, Indic, or Code-Switch.
Appropriate Med workflow.
The use case should determine the speech model.
Expand to new languages without rebuilding the app
Suppose the application first launches in English. Later it expands to Hindi, then Spanish, then Tamil.
English, on the same business application.
English + Hindi, on the same business application.
More supported languages, on the same business application.
The speech layer can expand while the core business workflow remains intact. This is the architectural advantage of a multilingual speech platform.
Do not assume every language combination
This distinction is important.
A language may be supported individually by Horizon Universal. That does not automatically prove that every possible mixed-language pair is available through the same Code-Switch route. Use Horizon Code-Switch where the required language combination is supported by the deployed configuration.
Do not hard-code assumptions about every possible language combination.
Check current language coverage
Language coverage grows over time. For the exact languages you can deploy today,use Shunya's current language-listing API.
This is more reliable than hard-coding a fixed language count into production logic.
Developers
Use streaming STT and TTS for real-time voice agents.
Use completed recordings for post-call transcription and intelligence.
Use explicit language codes where known, automatic language detection where appropriate, and Code-Switch routes for supported mixed-language conversations.
Use the current deployment's language listing when exact routable coverage matters.
Built for production multilingual voice AI
A production multilingual voice agent may need:
| Requirement | Shunya speech stack |
|---|---|
| Global Multilingual STT | |
| Indic STT | |
| Code-Switch STT | |
| Automatic Language Detection | |
| Streaming STT | |
| Batch STT | |
| Multilingual TTS | |
| Streaming TTS | |
| Batch TTS | |
| Cross-lingual Synthesis | |
| Mixed-language TTS | |
| Telephony Audio | |
| Speaker Diarization | |
| Word Timestamps | |
| Conversation Intelligence | |
| API Integration |
One conversational architecture. Multiple language experiences.
Questions
A Multilingual AI Voice Agent is a conversational application that can understand and respond to users across multiple supported languages using speech recognition, AI/application logic, and speech synthesis.
Yes. Horizon supports broad multilingual recognition across global and Indian languages.
Horizon Universal is Shunya's broad global-language speech-recognition model.
Horizon Indic is designed for supported Indian languages and Indian speech patterns.
Horizon Code-Switch is designed for conversations where supported languages naturally mix within the same sentence or interaction.
Yes. Hinglish is a core example of mixed-language conversational speech.
Code-Switch is designed for mixed-language conversations, but the exact supported language combination should be confirmed in the deployed configuration.
Yes. Horizon supports automatic language detection when language is not explicitly locked.
Not necessarily. When the expected language is known, explicitly locking it can reduce ambiguity, particularly for short audio.
Yes. The same business application can use different Shunya recognition and synthesis configurations according to the user's language.
Yes. Radiance is available as a multilingual speech-synthesis platform.
Yes. Radiance has a named voice catalogue across English and major Indian languages.
Radiance documents extended world-language synthesis, including languages beyond the core named Indic and English voice catalogue.
No. Not every language has dedicated named voices. Use the voices available in the current deployment.
Radiance documents cross-lingual synthesis, subject to the capabilities available in the relevant account and deployment.
Yes. Radiance documents mixed-language synthesis, including Hindi and English conversational speech.
Yes. Horizon supports real-time streaming transcription and Radiance supports streaming speech synthesis.
Radiance documents a first-audio streaming expectation of under 350 ms for relevant workflows.
Yes. Shunya's speech workflows support telephone-oriented audio including μ-law and A-law.
The surrounding application can change language configuration based on the user's request or conversation state, subject to the supported speech workflows.
Yes. Speaker diarization is available in supported STT workflows.
Yes. Summarisation is part of Shunya's supported batch conversation-intelligence layer.
Yes. Intent and sentiment are supported as batch intelligence capabilities.
Horizon Universal recognises 204 languages and Horizon Indic 55 Indian languages; Radiance Universal speaks 669 languages and Radiance Indic 23 Indic languages. When exact deployable coverage matters, use the current Shunya GET /languages endpoint rather than a hard-coded number.
No. The relevant mixed-language combination should be verified against the deployed Code-Switch configuration.
Yes. One speech platform can use different model and language routes according to the conversation.
Get started
Your users do not all speak one language. And multilingual users do not always stay inside one language. Use Horizon Universal for globalspeech. Use Horizon Indic for Indian-language conversations. Use Horizon Code-Switch for supported mixed-language interactions.Use Radiance to speak back through one multilingual voice platform. Test English, Hindi, regional languages, internationallanguages, Hinglish, code-switched speech, telephone audio, and the real conversations your users actually have.