Shunya LabsShunya LabsPlayground

Radiance · Tamil

Tamil Text to Speech

Convert Tamil text into natural, expressive AI speech for voice agents, customer conversations, narration, IVR, education, media, and real-time AI applications. Use Shunya Radiance to generate spoken Tamil from native Tamil text with dedicated Tamil voices, expressive delivery, streaming and batch synthesis, multilingual speech, and production-ready audio formats.

Murugan & Thangam Tamil voices11 expression styles<350ms first audioTA + EN Tanglish

All Text-to-Speech Languages

Murugan · Tamil

வணக்கம். உங்கள் ஆர்டர் நாளை காலை வந்து சேரும்.

Conversational delivery · Radiance
Voice · MuruganExpression · ConversationalTamil · Streaming<350ms first audio

Tamil TTS

Tamil Text in. Tamil Voice Out.

Tamil speech synthesis needs to do more than pronounce characters. Natural speech depends on the complete sentence - including Tamil grammar, names, numbers, English terminology, punctuation, speaking style, and conversational context. Radiance includes dedicated Tamil voices and supports Tamil as part of Shunya's Indic speech-synthesis stack.

2

Dedicated named Tamil voices

46

Named voices across the Indic + English catalogue

11

Expression styles

<350ms

First-audio streaming latency

CapabilityRadiance · Tamil Text to Speech
Native Tamil Script✓
Dedicated Tamil Voices✓
Male + Female Voice✓
Tanglish / Mixed Text✓
Streaming Synthesis✓
Batch Synthesis✓
Expression Control✓
Speed Control✓
Voice Cloning✓
Multiple Audio Formats✓
API Integration✓

Try it yourself

Hear the Tamil Your Application Actually Needs

Don't evaluate Tamil TTS only with a prepared demo sentence. Try a customer response, product name, appointment
message, notification, narration, Tamil-English sentence, or dynamically generated AI response.

Tamil voices

Two Native Tamil Voice Identities, One Larger Voice Catalogue

Radiance's named voice catalogue includes dedicated male and female speakers for Tamil.

Tamil · Male

Murugan

Use for conversational AI, narration, customer interactions, notifications, and general speech generation.

Tamil · Female

Thangam

Use for voice agents, customer experiences, educational material, media, and general Tamil synthesis.

Tamil language code

ta

46 voices

One male and one female speaker across the named catalogue

LanguageMaleFemale
EnglishVarunNisha
HindiRajeshSunita
TamilMuruganThangam
TeluguVishnuLakshmi
BengaliArjunPriyanka
MarathiSiddharthAnanya
KannadaKiranShreya
MalayalamKrishnanDeepa
GujaratiRakeshPooja
PunjabiGurpreetSimran

Tamil script

Generate Speech Directly from தமிழ்

Tamil has its own writing system. Applications should be able to send natural Tamil text directly instead of first converting it into Roman characters.

Tamil inputஇன்று உங்கள் சந்திப்பு மாலை நான்கு மணிக்கு உள்ளது.RadianceSpoken Tamil

The input can remain in native Tamil script.

Tamil script

தமிழ்

Romanised Tamil

Latin characters

Ungal appointment naalai kaalai pathu manikku irukkirathu.

Both are ways of writing Tamil. Radiance speaks native Tamil script directly, so your application can send Tamil text exactly as it is written.

Tamil + English

Because Real Tamil Conversations Are Often Tanglish

Many Tamil speakers naturally combine Tamil and English. Especially in customer support, technology,
banking, e-commerce, workplace conversations, healthcare, and mobile applications.

Appointment confirmation

உங்கள் appointment நாளை morning 10 மணிக்கு confirm ஆகிவிட்டது.

Payment update

உங்கள் payment successfully process ஆகிவிட்டது.

Customer support

App open ஆகுது but login button work ஆகவில்லை.

Product conversation

உங்கள் order dispatch ஆகிவிட்டது. Tracking link SMS-ல் வரும்.

The Shunya TTS playground supports mixed Tamil and English input.

One sentence · Tamil + EnglishRadianceOne continuous voice

The application does not need to manually generate separate Tamil and English audio clips for every language change.

Expressive Tamil speech

Keep the Words. Change the Delivery.

A Tamil voice agent should not necessarily sound like an audiobook narrator. A notification should

not necessarily sound like a newsreader. Radiance provides 11 expression styles.

Neutral

General-purpose Tamil speech.

Conversational

Natural dialogue for customer interactions and voice AI.

Narrative

Storytelling and longer-form content.

News

Structured informational delivery.

Happy

Positive and upbeat speech.

Sad

Softer, subdued delivery.

Angry

More intense expression.

Fearful

Anxious or tense delivery.

Surprised

Reactive speech.

Disgust

Disapproving expression.

Enthusiastic

Energetic delivery.

Same text: உங்கள் கோரிக்கை வெற்றிகரமாக நிறைவேற்றப்பட்டது.Neutral · Conversational · Enthusiastic

The sentence stays the same. How it sounds changes.

Real-time Tamil TTS

Generate Tamil While the AI Is Still Responding

Fixed prompts can be generated ahead of time. Conversational AI needs speech dynamically.Radiance provides WebSocket streaming for low-latency speech generation.

<350ms

First-audio latency

LLM generates responseTamil sentence becomes availableRadiance begins synthesisAudio chunks stream backUser hears Tamil speech

Speech begins as synthesis progresses, so users do not wait for a long response to finish generating.

Streaming or batch

Generate Speech Now or Ahead of Time

Radiance supports two synthesis modes.

Streaming

For live conversations

Use WebSocket synthesis when the user is waiting for the response.

Best for:

  • Tamil voice agents
  • Customer support
  • Conversational AI
  • IVR
  • Interactive assistants
  • Live applications
  • Real-time information services

Batch

For complete content

Use HTTP synthesis when the full audio file can be generated before playback.

Best for:

  • Narration
  • Announcements
  • Notifications
  • Learning material
  • Media
  • Pre-recorded prompts
RequirementStreamingBatch
Tamil Voice Agents✓-
Live Conversations✓-
Complete Audio Files-✓
Notifications✓✓
Narration✓✓
WebSocket✓-
HTTP POST-✓

Control the audio

Tamil Speech for the Environment Where It Will Actually Play

Radiance supports seven output formats.

FormatCommon use
PCMLow-latency applications
WAVHigh-quality editing
MP3Web and general delivery
OGG OpusStreaming applications
FLACLossless audio
μ-lawPSTN / telephony
A-lawSIP / telephony

Speed control

0.25× → 4.0×

Adjust speaking speed from 0.25× to 4.0×.

Trim silence

Remove unnecessary silence

Trim the silence before and after generated speech, so prompts and replies start on time.

Quality

Configure synthesis quality

Match output quality to the channel, from compact telephony audio to high-quality files for media.

One Tamil voice - different output environments: Web · Mobile · Telephony · Media · Voice agents

Cross-lingual voices

A Tamil Voice Doesn't Have to Speak Only Tamil

Radiance separates voice identity from the language of the input. Shunya's documentation states that any named voice can speak any supported language. And voices associated with other languages can also synthesize Tamil.

Tamil voice

Murugan

Can synthesize supported text beyond Tamil.

Tamil voice

Thangam

Can synthesize supported text beyond Tamil.

Example

Choose Murugan, then provide Tamil text, English text, or another supported language.

Voice controls the vocal character. Text + language control what is spoken. This makes it possible to maintain a chosen voice identity across multilingual experiences.

Voice cloning

Create Tamil Speech Using an Authorised Reference Voice

Sometimes built-in voices are enough. Sometimes the voice itself is part of the product. Radiance supports voice cloning from a short reference recording.

3-6 seconds

Reference-audio range

01

Provide an authorised voice sample

Short clean recording.

02

Provide the transcript

Transcript of the sample.

03

Enter new Tamil text

Generate new Tamil speech using characteristics from the reference voice.

Reference · short clean recordingNew text: நாளை காலை உங்களை மீண்டும் தொடர்பு கொள்கிறோம்.Generated speech

Responsible use: Only clone voices where the required rights and voice-owner permission exist for the intended use.

Tamil voice agents

Give Conversational AI a Tamil Voice

A voice agent needs both a listening layer and a speaking layer.

User speaks

என் order எப்போது வரும்?

Horizon

Converts Tamil speech into text.

LLM / Agent

Understands the question and generates a response.

Radiance

Generates spoken Tamil.

User hears

உங்கள் ஆர்டர் நாளை வந்து சேரும்.

STT → LLM → TTS

Radiance becomes the speaking layer of a complete Tamil conversational AI experience.

User speaksHorizonLLM / AgentRadianceUser hears

Real-world use cases

Tamil Speech Wherever Software Needs to Talk to Users

AI Voice Agents

Generate dynamic Tamil speech for conversational AI.

Customer Support

Provide Tamil-language automated support and conversational responses.

Banking & Financial Services

Generate payment information, reminders, service messages, and customer communication.

IVR & Telephony

Create Tamil menus, confirmations, notifications, and dynamic phone responses.

Healthcare

Speak appointment details, reminders, and patient-facing messages.

E-commerce

Speak order updates, delivery messages, return information, and customer responses.

Government Services

Provide spoken Tamil interfaces for citizen-facing digital services.

E-learning

Generate Tamil lessons, instructions, explanations, and educational audio.

Media & Narration

Convert Tamil scripts and written content into spoken audio.

Accessibility

Provide spoken alternatives to written Tamil interfaces and information.

Developers

Add Tamil Speech Generation to Your Application

Radiance Indic provides HTTP batch synthesis and WebSocket streaming for Tamil. Set model to radiance-indic, language to ta, and voice to Murugan or Thangam.

basic-request.json

{
  "model": "radiance-indic",
  "language": "ta",
  "input": "<Conversational> வணக்கம். இன்று நான் உங்களுக்கு எப்படி உதவலாம்?",
  "voice": "Murugan",
  "response_format": "mp3"
}

Batch endpoint

POST /v1/audio/speech

https://ttsv2.shunyalabs.ai/v1/audio/speech

Streaming endpoint

WebSocket realtime

wss://ttsv2.shunyalabs.ai/v1/realtime

Input

Tamil text

From an application, content platform, customer workflow, or LLM.

Generate

Batch or streaming

Create a complete audio response through batch synthesis or receive progressive audio chunks through streaming.

Configure

Choose delivery

  • Voice
  • Language
  • Expression
  • Speed
  • Output format
  • Silence trimming
  • Quality

Output

Use the speech

  • Voice agents
  • IVR systems
  • Web applications
  • Mobile apps
  • Customer-support platforms
  • Learning platforms
  • Media workflows
Explore the TTS API

Built for production

Beyond the Play Button

A convincing Tamil audio demo is only the beginning. Production applications need dedicated voices, mixed-language handling,low-latency streaming, APIs, audio-format control, telephony support, expression, cloning, and multilingual expansion.

RequirementRadiance
Tamil Text to Speech✓
Tamil Language Codeta
Native Tamil Script✓
Tamil Male VoiceMurugan
Tamil Female VoiceThangam
Named Voice Catalogue46
Expression Styles11
Tanglish Input✓
Batch Generation✓
Streaming Generation✓
First Audio<350ms
Speed Control0.25×-4.0×
Audio Formats7
Telephony Formats✓
Cross-lingual Synthesis✓
Voice Cloning✓
API Integration✓
Voice Agent Integration✓
Tamil textRadianceTamil speechWeb · Mobile · Telephony · Voice agents · Media · AI applications

Questions

Frequently Asked Questions

What is Tamil Text to Speech?

Tamil Text to Speech uses speech-synthesis technology to convert written Tamil into spoken audio.

Does Shunya support Tamil Text to Speech?

Yes. Tamil is supported by Radiance and uses the language code ta.

Which Tamil voices are available?

Shunya's current named catalogue includes Murugan (male) and Thangam (female) for Tamil.

Can Shunya read native Tamil script?

Yes. Tamil is supported using its native Tamil script.

Can Shunya handle Tamil mixed with English?

Yes. The Shunya TTS playground supports mixed Tamil and English input, and Radiance is built for Tanglish and other mixed-language speech.

How many named voices does Radiance have?

Shunya has 46 named voices, with one male and one female speaker across its 23-language Indic catalogue plus English.

Can I use a Tamil voice to speak English?

Yes. Radiance supports cross-lingual synthesis. The voice controls vocal identity while the input text controls the language being spoken.

Can another Shunya voice speak Tamil?

Yes. Any voice can synthesize any supported language.

Can Tamil TTS work in real time?

Yes. Radiance provides WebSocket streaming for real-time synthesis.

How fast does streaming begin?

Shunya's current documentation reports first audio in under 350 ms for streaming TTS. Actual end-user latency can vary with network, infrastructure, input, and configuration.

Can I control the speaking style?

Yes. Radiance supports 11 expression styles.

Can I control speaking speed?

Yes. Speed can be configured from 0.25× to 4.0×.

Which audio formats can I generate?

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

Can Tamil TTS be used for telephony?

Yes. μ-law and A-law output formats support telephony-oriented workflows.

Can I clone a Tamil voice?

Radiance supports voice cloning using approximately 3-6 seconds of clean reference audio for supported voice-cloning workflows.

Can Tamil TTS be used for voice agents?

Yes. Streaming TTS can serve as the speech-generation layer after an LLM or conversational agent generates its Tamil response.

Is Tamil TTS available through an API?

Yes. Radiance supports both HTTP batch synthesis and WebSocket streaming.

Get started

Turn Tamil Text into Speech

Don't judge Tamil TTS from our prepared sentence. Test yours. Try a customer response, Tamil name, product term, appointmentreminder, Tanglish sentence, payment message, narration, voice-agent response, or dynamically generated text.Choose Murugan or Thangam. Change the expression. Hear how Shunya turns your Tamil text into speech.