Shunya LabsShunya LabsPlayground

Radiance · English

English Text to Speech

Turn English text into natural, expressive speech for voice agents, customer conversations, applications, narration, and real-time AI experiences. Choose a voice, control the delivery, and generate spoken English through Shunya Radiance.

46 speaker voices11 expression styles<350ms first audio7 audio formats

All Text-to-Speech Languages

Nisha · English

Hello, thanks for calling. I can help you check your account, update your details, or answer a question about your recent transaction.

Conversational delivery · Radiance
Voice · NishaExpression · ConversationalEnglish · Streaming<350ms first audio

English TTS

English Speech, built for more than Reading text Aloud

Text-to-speech is not only about converting words into audio. Production speech needs the right voice, pacing, expression, output format, and response time for the application using it.

46

Built-in speaker voices available across the Radiance voice catalogue

11

Expression styles for changing how speech is delivered

<350ms

First audio in streaming mode for real-time applications

7

Audio output formats for web, production, streaming, and telephony

CapabilityRadiance · English Text to Speech
English Male VoiceVarun
English Female VoiceNisha
Expression Styles11
Batch Synthesis✓
Streaming Synthesis✓
Cross-lingual Synthesis✓
Voice Cloning✓
Speed Control0.25× - 4×
Audio Formats7

Try it yourself

Hear your English text, not a Prepared Demo

The best way to evaluate a voice is with the words your application will actually say.

English voices

Start with English. Choose the Voice that Fits

Radiance includes two named English voices in its standard voice catalogue.

English · Male

Varun

Built-in English speaker available through the Radiance API and playground.

English · Female

Nisha

Built-in English speaker available through the Radiance API and playground.

But the voice catalogue does not stop at two English speakers. Radiance separates voice identity from the language being spoken. Any supported voice can synthesize supported languages, enabling teams to experiment with different vocal characteristics without changing the input language.

46 voices

One voice catalogue. Cross-lingual synthesis built in.

LanguageMale voiceFemale voice
EnglishVarunNisha
HindiRajeshSunita
BengaliArjunPriyanka
TamilMuruganThangam
TeluguVishnuLakshmi
KannadaKiranShreya
MarathiSiddharthAnanya
MalayalamKrishnanDeepa
PunjabiGurpreetSimran
UrduSalmanFatima

The input text controls the language. The selected voice controls the vocal character.

Expressive speech

The sentence stays the same. The Delivery Changes.

Real conversations do not use one tone for everything. A support response, an announcement, an educational explanation,

and a story may use the same language while requiring completely different delivery. Radiance supports

11 expression styles for controlling how generated speech sounds.

Conversational

Natural everyday delivery for voice agents, assistants, and customer interactions.

Narrative

Long-form delivery for stories, articles, explanations, and narration.

News

Structured delivery for announcements and informational content.

Happy

Brighter delivery for positive interactions and messages.

Enthusiastic

Higher-energy speech for engaging experiences.

Sad

Softer delivery for situations where the tone needs to reflect the content.

And moreExpression can be selected according to the context instead of forcing every sentence through the same speaking style.

Real-time speech

Built for Applications that need to Speak Back

Pre-generated audio can wait. A voice agent cannot. Radiance supports both streaming and batch synthesis,using the same speech platform for two different production requirements.

<350ms

First audio in streaming mode

Streaming

Generate speech while the response is happening

Open a persistent WebSocket connection and receive audio progressively as synthesis takes place.

Best suited for:

  • Voice agents
  • Conversational AI
  • Interactive assistants
  • Live customer support
  • Real-time applications

Batch

Generate complete audio in one request

Send the complete English text and receive the finished audio output.

Best suited for:

  • Narration
  • Notifications
  • Educational content
  • Pre-generated IVR prompts
  • Media workflows
  • Audio content
RequirementStreamingBatch
Real-time playback✓-
Complete file output-✓
Voice agents✓-
Narration✓✓
WebSocket✓-
HTTP API-✓

Audio control

Generate English Speech for the channel It will Actually use

The same audio format is not right for every application. Web playback, production audio, low-latency pipelines,

archival workflows, and telephony have different requirements. Radiance supports seven output formats.

FormatCommon use
MP3Web playback and general applications
WAVHigh-quality audio workflows
PCMReal-time and low-latency pipelines
OGG OpusEfficient streaming and web audio
FLACLossless audio
mu-lawTelephony systems
A-lawTelephony systems

Speed control

0.25× → 4.0×

Adjust speech speed from 0.25× to 4.0×. Applications can control delivery speed without creating a separate voice model.

Silence control

Trim silence

Speech output can also be configured to trim silence when tighter audio is required.

Voice cloning

A voice that can say New Things

Static voice recordings only work for sentences that have already been recorded. Voice cloning creates a reusable synthetic voice from a short reference sample.

3-6 seconds

Reference audio required for Radiance voice cloning

01

Provide a voice sample

Supply a clean reference recording.

02

Create the voice

The reference is used to establish the voice characteristics for synthesis.

03

Enter new text

Generate English speech that was never present in the original recording.

04

Go cross-lingual

Use the voice across supported languages instead of building an entirely separate voice identity for every language.

Built for consistency: One voice identity can remain part of the product as the words - and potentially the language - change.

Real-world use cases

English TTS is only useful when it Fits the Product

Voice Agents

Turn dynamically generated responses into spoken English during live AI conversations.

Customer Support

Create automated spoken responses for account questions, service requests, updates, and self-service workflows.

IVR & Telephony

Generate dynamic phone prompts while supporting telephony-ready mu-law and A-law audio.

E-learning

Convert lessons, explanations, instructions, and educational material into spoken English.

Media & Narration

Generate audio for articles, stories, scripts, presentations, and other content.

Accessibility

Offer spoken alternatives to written interfaces and digital information.

Notifications

Generate account alerts, reminders, order updates, appointment messages, and other dynamic speech.

AI Applications

Add a voice layer to assistants, copilots, conversational products, and other generative AI experiences.

Developers

From English text to audio in one API workflow

Radiance can be integrated through HTTP for batch synthesis or WebSocket for streaming speech.

basic-request.json

{
  "model": "radiance-indic",
  "input": "Hello, how are you today?",
  "voice": "Varun",
  "language": "en",
  "response_format": "mp3"
}

Input

English text

From your application, content system, user workflow, or LLM.

Generate

Batch or streaming

Create complete audio through batch synthesis or receive progressive audio through streaming.

Configure

Choose delivery

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

Output

Use the speech

  • Voice agents
  • Phone systems
  • Web applications
  • Mobile apps
  • Learning platforms
  • Media workflows
Explore the TTS API

Built for production

Beyond the Voice Sample

Generating one good sentence is not the same as operating a speech product. Production teams also need streaming, audiocontrols, APIs, multilingual expansion, deployment flexibility, and consistent voice behaviour.

RequirementShunya Radiance
English Text to Speech✓
Male + Female English Voices✓
Expression Control✓
Streaming TTS✓
Batch TTS✓
Cross-lingual Synthesis✓
Voice Cloning✓
Multiple Audio Formats✓
Telephony Audio✓
API Integration✓
LLM → TTS Workflows✓

LLM → TTS

Radiance can sit directly after an LLM in a conversational pipeline.

User speaksSTTLLMRadianceUser hears response

This makes English TTS part of a complete voice interaction rather than a standalone audio-generation step.

Questions

Frequently Asked Questions

What is English Text to Speech?

English Text to Speech converts written English into spoken audio using a speech synthesis model.

Which English voices are available in Shunya?

Radiance includes Varun, a male English voice, and Nisha, a female English voice, in its named voice catalogue.

Can I use English Text to Speech for voice agents?

Yes. Radiance supports streaming synthesis, designed for applications such as voice agents and real-time conversational experiences.

Does Shunya support different speaking styles?

Yes. Radiance supports 11 expression styles for changing how generated speech is delivered.

Can I change the speech speed?

Yes. Speech speed can be configured from 0.25× to 4.0×.

Which audio formats are supported?

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

Can I create a custom English voice?

Radiance supports voice cloning using a short reference audio sample.

Can the same voice speak another language?

Yes. Radiance supports cross-lingual synthesis across its supported language set.

Get Started

Test English Text to Speech with your Own Words

Don't judge a voice on our sample. Give it your text. Try the names, numbers, product terms, customer responses,scripts, or AI-generated sentences your application actually needs to speak.Choose a voice. Change the expression. Hear the result.