Text-to-Speech

Lifelike speech, in real time.

Turn text into natural, expressive voice — fast enough for live calls, in 22 Indian languages + English, with your own cloned voice if you want it.

POLLAX TEXT TO SPEECH · NATURAL VOICES · FIRST BYTE ~75MS · MP3 24KHZ · STREAMING AUDIO · POLLAX TEX03PLX·TTSTXTPRSVOXOUT
Class 03

03Text to Speech

First byte~75ms
FormatMP3 · 24kHz
Languages22 + EN

Voice

Aditi · Hindi
Fig. 01 — Text-to-Speech
Under the hoodLive readout

Text in,a voice out.

Send a sentence, get audio back while it's still being generated — so the caller hears the agent start speaking almost at once.

  1. A /VoicePick a voice and language — Aditi in Hindi here.
  2. B /First byteAudio starts streaming in ~75ms.
  3. C /FormatMP3 at 24kHz, ready for phone and web.
Live demo

See it in action

Live Demo

Input text

55 charactersMatches the recorded English (India) sample

Voice library

Ready
Meera
English (India)FemaleIndian

46 voices

Capabilities06 / Index

What you get.

01

Lifelike voices

Natural, expressive text-to-speech that sounds human, with multiple voice profiles per language.

02
Englishहिन्दीதமிழ்తెలుగుবাংলাಕನ್ನಡ+17

22 Indian languages + English

22 Indian languages + English, with native pronunciation and accent support.

03
~75msfirst byte

Real-time streaming

Sub-second first-byte latency — fast enough for live, interruptible phone conversations.

04
30s sample your voice

Voice cloning

Clone a brand or spokesperson voice from a short sample and use it across every agent.

05
Speed
Pitch
Emphasis

Fine control

Tune speed, pitch, and emphasis with SSML for pronunciation and pacing that fit your script.

06
₹/minusage-based

Built for scale

Transparent, usage-based pricing that stays affordable from the first call to the millionth.

Engines

Pick the right voice engine

Trade latency for richness, or richness for latency — switch per request.

Flash / Turbo

Ultra-Low Latency

Optimized for real-time applications where speed is critical. Produces natural-sounding speech in ~75ms with support for 22 Indian languages + English and a 40,000 character limit per request.

  • ~75ms latency
  • 22 Indian languages + English
  • 40,000 char limit
  • Ideal for live calls & voice bots

Multilingual v2 / v3

High Quality

Premium voice synthesis with rich naturalness and emotional range across 22 Indian languages + English. ~250–300ms latency — perfect for IVR, content narration, and branded voices.

  • ~250–300ms latency
  • 22 Indian languages + English
  • Emotionally expressive
  • Ideal for IVR & narration
API capabilities

Every voice control, explained

Click a parameter to see how it shapes speech — and the request that turns it on.

Voice

voice_id

Pick a named voice profile — or a cloned brand voice — so every agent sounds consistent across calls.

Live example

Anushka

Indic · warm

selected

Arjun

Indic · clear

Priya

en-IN · support

Request
{
  "text": "Welcome to Pollax support.",
  "voice_id": "pollax-indic-anushka",
  "model": "flash"
}
Response
{
  "audio_url": "https://cdn.pollax.ai/tts/abc.mp3",
  "voice_id": "pollax-indic-anushka",
  "duration_ms": 1840
}
Use cases

Power your applications

Natural speech for every scenario

Customer Service

  • IVR systems
  • Voice notifications
  • Call automation
  • Support bots

Content Creation

  • Audiobooks
  • Podcasts
  • Video narration
  • E-learning

Accessibility

  • Screen readers
  • Text readers
  • Navigation
  • Educational tools

Marketing

  • Ad voiceovers
  • Product demos
  • Promo content
  • Social media
At a glance

Real-time, production-ready

Spec sheet04
<300ms
First-byte latency
22
Indian languages + English
40+
Voices
99.99%
Uptime
Languages

22 Indian languages + English

Native pronunciation and scripts — with the ability to switch language mid-call based on the speaker.

Indian languages

English (India)
Hindiहिन्दी
Bengaliবাংলা
Tamilதமிழ்
Teluguతెలుగు
Marathiमराठी
Gujaratiગુજરાતી
Kannadaಕನ್ನಡ
Malayalamമലയാളം
Punjabiਪੰਜਾਬੀ
Odiaଓଡ଼ିଆ
Assameseঅসমীয়া
Urduاُردُو
Bodoबरो
Dogriडोगरी
Kashmiriکٲشُر
Konkaniकोंकणी
Maithiliमैथिली
ManipuriMeitei
Nepaliनेपाली
Sanskritसंस्कृतम्
SantaliSantali
Sindhiسنڌي

Also available for international callers

English (US)
English (UK)
English (Australia)
English (Canada)
English (Singapore)
English (South Africa)
English (Philippines)
SpanishEspañol
Spanish (Mexico)Español
FrenchFrançais
GermanDeutsch
ItalianItaliano
Portuguese (Brazil)Português
DutchNederlands
PolishPolski
RussianРусский
UkrainianУкраїнська
Arabic (UAE)العربية
Arabic (Saudi)العربية
Japanese日本語
Korean한국어
Chinese (Mandarin)中文
Thaiไทย
VietnameseTiếng Việt
TurkishTürkçe
IndonesianBahasa Indonesia
MalayBahasa Melayu
FilipinoFilipino
FAQ04 / Questions

Questions,answered.

The short answers. The docs have the long ones.

  1. Streaming and full-file output in common formats (MP3, WAV, PCM) suitable for telephony and web playback.

StartNow

Hear itfor yourself.

Generate your first audio in minutes with a free API key.