Record
Thirty minutes of clean studio audio in the voice you want, read from our script in Hindi, English (US) and Hinglish. We help with the script and the session.
आधे घंटे की recording, बस.
Voice AI that speaks before you can blink. Natural Hindi, Hinglish and English, at 10 paise per 1,000 characters.
First audio before you can blink.
A blink takes 100 to 400 milliseconds. Our server starts speaking in under 10, and a browser in India hears it in about 175, network included.
- <10 ms on the server
- 175 ms heard in a browser
- 7× real time
Rented voices cost about 2.5 cents a minute. Ours: 10 paise per 1,000 characters.
A rented voice is rented compute plus a vendor margin: 2.5 cents (₹2) or more a minute. Ours is 10 paise per 1,000 characters, about a minute of speech, because the model is ours and it runs on ordinary servers.
- 10pper 1,000 characters
- ₹100minimum top-up
Hindi, English (US), English (IN), Hinglish. Then the world's languages.
Trained on how people actually talk: switching languages mid-sentence, numbers, amounts and dates read the local way, codes and acronyms spelled out. More languages are in training now.
- हिंदी
- English (US)
- English (IN)
- Hinglish
- தமிழ்
- తెలుగు
- मराठी
- বাংলা
- ಕನ್ನಡ
No per-stream fees. Add servers, add capacity.
One four-core server carries 24 live streams and makes 30 seconds of speech every second. Need more? Add servers, in our cloud or your data centre, at the same price.
- 24 streams per server
- 30× real time per server
- Your data centre or ours
Give us the voice. We train the model for you.
Record your brand voice, an agent, an anchor, a founder, and we return a model trained on it: your timbre, your pronunciations, your pace. Same price, same speed, yours to run wherever you like.
- 30 min of recordings
- Your model
- Same price
- Runs anywhere
Why Vartaloop
Vartaloop TTS
Voices that start speaking before the sentence ends.
Natural, expressive Hindi, Hinglish and English, streamed from a plain API. Names, numbers and amounts read the way a person reads them, on a model we built and an engine we wrote.
- 01Reads it right $12.50 · ₹4,250 · 12 अक्टूबर · OTP digits · EMI, KYC
- 02Switches mid-sentence Hindi and English in one breath, the way people talk
- 03Your pace 24 kHz, from 0.5× to 2×, set per request
Vartaloop TTSStudioStreaming
नमस्ते, electricity repair के लिए आज सुबह बात हुई थी। Nivedita Xpress Distribution Company के case में मेरे अलावा alternate contact सिद्धार्थ भट्टाचार्य हैं। Callback +44 00000 19024 पर करें। Support app का version v7.07.1 है; processing estimate ₹17.99 है। इसे payment approval न मानें। मैं इन details की confirmation कर रही हूँ। आपने मेरा phone number groups में लिखने को कहा था; अब सही number है: +44 00000 19024। पहले वाला number गलत था; ऊपर लिखे सही number का हर digit जरूरी है। कृपया पुराने number पर call न करें, क्योंकि वह पड़ोसी का है और वे घर पर नहीं होंगे। शाम 6:30 के बाद मैं available रहूँगी। Meter की photo पहले ही भेज दी है, इसलिए काम शुरू करने से पहले दोबारा आने की जरूरत नहीं है। कृपया आने का estimated time message में बता दें। Reply के साथ +44 00000 19024 जोड़ दें। इस हिस्से के बिना confirmation incomplete रहेगी और फिर से check करना होगा।
“Hello, we spoke this morning about the electricity repair. For the Nivedita Xpress Distribution Company case, the alternate contact besides me is Siddharth Bhattacharya. Call back on +44 00000 19024. The support app is version v7.07.1; the processing estimate is ₹17.99. Do not treat this as payment approval. I am confirming these details. You asked me to write my phone number in groups; the correct number is +44 00000 19024. The earlier number was wrong; every digit of the number above matters. Please do not call the old number: it belongs to a neighbour and they will not be home. I will be available after 6:30 pm. I have already sent the meter photo, so there is no need to visit again before starting the work. Please message the estimated arrival time. Add +44 00000 19024 to the reply. Without that part the confirmation stays incomplete and will have to be checked again.”
Real outputAditya · English (IN)Production voice · 47 voices live, your own on request
Unedited model output, 24 kHz. Forty-seven production voices are live: twenty-one Hinglish — Saanvi and Sahil first, each with three expressions (excited, sad, whisper), and nineteen new voices from the deepest to the brightest register — eighteen English (US), nine female and nine male, Kiara and Kevin first among them; and eight English (IN), four female and four male, Ananya and Arjun first among them. Pick a language and a voice above to hear each one; your own voice trains on the same engine at the same price.
The numbers
Faster than a blink, on ordinary servers.
Comparisons below are like for like: audio heard end to end, network included. We publish how each number was measured.
<10 msfirst audio on the server
175 msfirst audio heard in a browser in India
24live streams on one four-core server
30×real time per server
Time to first audio
end to end, lower is better · rented voices: independent medians, Oct 2026Price per minute of speech
list prices, October 2026, converted at ₹84 a dollar · ours is per 1,000 characters, about a minute of speechHow we measure: first audio is the time from text in to the first audio frame, on the server or as heard in a browser in India on our Mumbai service. Capacity was measured on a four-core cloud server on 3 November 2026 with paragraph-length text and no gaps in playback.
Your voice
Give us the voice. We give you the model.
Our stock voices are good. Yours is better for your brand: the agent your customers already know, the anchor from your ads, the founder. Record it once; we train a model on it and hand it back at the same price and the same speed, to run in our region or on your own servers.
We train
The model learns the timbre, the pace and the pronunciations of that voice while keeping everything it already knows about names, numbers and code-switching.
Two to three weeks, end to end.
You ship
Your voice behind the same API at the same 10 paise per 1,000 characters, in our cloud or inside your data centre. The model is yours.
Same price. Same speed. Your voice.
Pricing
One price, per 1,000 characters.
We own the model and it runs on ordinary servers. No seats, no setup fee, no card to start.
Vartaloop TTSStreaming API
The voice, streamed.
10pper 1,000 charactersOpus and PCM, about a minute of speech · WAV 12p · any of our voices or yours
- English (US), English (IN), Hindi and Hinglish voices; names, numbers and amounts read right
- Streaming WebSocket and REST, first audio before you can blink
- No per-stream fee, in our cloud or your data centre
- Your own voice, trained for you, at the same price
- More languages as they leave training, same price
Opus (default) and PCM10p per 1,000 charactersprepaid credits from ₹100 (10 lakh characters), no card on file
WAV12p per 1,000 charactersthe same voices and speed, 2p more for the WAV format
Launch offer: the first 1,000 sign-ups get 10 lakh characters free, once the e-mail is verified.
A character is a Unicode character of the text you send, trimmed and counted before normalisation: every मात्रा, halant and nukta counts as one (नमस्ते is 6), and spaces and punctuation count. Pay as you go is prepaid: top up from ₹100 by UPI, card or net banking through Razorpay, 18% GST extra; when credits run out the API answers 402 until you top up, so there is never a surprise bill.
Built for production
Honest under load. Yours to run.
Your data, your region
Run in our Mumbai service or inside your own data centre.
A clear contract at capacity
If every server is busy you get a 503 and a retry time before any audio. A stream that has started is never cut short.
Consent on record
A custom voice is trained only with the speaker's recorded consent. The model is yours.
Ordinary hardware
No scarce GPUs: it runs on standard CPU servers, so capacity arrives in minutes.
Questions
The short answers.
What is Vartaloop?
Vartaloop is a text-to-speech platform of InfiniSync Consulting (OPC) Private Limited: a streaming text-to-speech API built on our own voice model and engine. Send text over REST or WebSocket and get natural speech back as it is generated, in Hindi, Hinglish, English (India) and English (US).
How fast is Vartaloop text-to-speech?
Before you can blink. A blink takes roughly 100 to 400 milliseconds. The first audio leaves our server in under 10 milliseconds, and a browser in India hears it in about 175 milliseconds, network included. A minute of speech is generated in about eight seconds.
How much does it cost?
10 paise per 1,000 characters, billed in rupees. A thousand characters is about a minute of speech. That rate is for Opus, the default, and PCM; WAV is 12 paise per 1,000. The first 1,000 sign-ups get 10 lakh characters free.
Which languages and voices are available?
47 voices: 21 Hinglish, 18 English (US) and 8 English (India). Hinglish voices speak Hindi, English and code-mixed sentences. Tamil, Telugu, Marathi, Bengali and Kannada are in training.
Does it read numbers, amounts and OTPs correctly?
Yes. A built-in normaliser reads currency amounts, dates, phone numbers, OTP digits and acronyms such as EMI and KYC the way a person would, in Hindi and in English.
How many streams can run at the same time?
One four-core server carries 24 live streams and makes 30 seconds of speech every second. There is no per-stream fee: capacity grows by adding servers. If every server is busy, the API answers 503 with a retry time before any audio, and a stream that has started is never cut short.
Can I run Vartaloop on my own servers?
Yes. It runs on ordinary CPU servers, in our cloud or inside your own data centre, so your data can stay in your region.
Can you create a custom voice for my brand?
Yes. Record about thirty minutes of clean studio audio, with the speaker's consent on record, and we train a model on that voice in two to three weeks. It costs the same per character and runs at the same speed.
How do I start?
Create a free account at tts.vartaloop.ai, make an API key, and follow the quickstart at docs.vartaloop.ai. Your first audio takes about a minute.
Talk to us
Every message, said out loud — in your customers' languages.
Bring the sentences your product needs to say and the volume you need to say them at. Thirty minutes is enough to hear them in our voices and work out your numbers.
30-minute intro call
Hear it live, then talk numbers.
With Puru Chaudhary, founder & CTO. Pick a slot that suits you and the invite lands in your calendar with a video link.
- Your sentences, in our voices, live
- Your own voice: what to record, how long it takes
- Unit economics, the stack and the roadmap
The founders
Two founders, one stack.
One of us runs the company, the customers and the pilots. The other trains the speech recognition, the language model and the voices, and builds the platform they run on. Both have been here since the first call, and both have their own money in it.
Rajat MangotraFOUNDER & CEO
Runs Vartaloop and scales it, from the company and its customers to the pilots and the money. He has spent eight years building AI and ML products across retail, e-commerce, fintech, education and hospitality, with a record of making systems faster, cheaper and bigger, often cutting compute costs by 90% or more. Most recently, as co-founder of QuickDial AI, Vartaloop’s US sibling, he helped bring a CPU-only voice-agent stack down to a quarter of a cent a minute. An alumnus of IIT Kanpur.
Purushottam (Puru) ChaudharyFOUNDER & CTO · AI INFERENCE ENGINEER
Trained the voices and the speech recognition, wrote the engine that runs them on ordinary servers, and built the platform above it. Fifteen years of software for GE HealthCare, S&P Global, Bristol Myers Squibb and State Street; three years training models; three companies founded. Author of The Inference Mechanic.