Quick TTS · US English text-to-speech Live

Voice that costs next to nothing.

$2per million characters
0.2¢for about a minute of speech

Quick TTS speaks natural US English from a model we trained and an engine we wrote. No vendor sits in the middle taking a margin, so you pay a fraction of what voice costs you today. One API call and it is talking.

7–20×below the big voice APIs
64 msto first sound
18US English voices

The bill for these words

Quick TTS0.000¢
Others average0.000¢

Press play to start the meter

Try it

Type anything. Hear it back.

Write a line your product would say, pick a voice and listen. A sentence costs us a few thousandths of a cent, so go ahead.

0 / 300 charactersthis costs 0.000¢
Voice

Price comparison

Same job. A fraction of the bill.

What a million characters of speech costs at list price, taken from each company's own pricing page.

Price per million charactersUS dollars · list price · lower is better
Quick TTS$2
OpenAI tts-1$157.5× more
Deepgram Aura-2$3015× more
Cartesia Sonic$3819× more
ElevenLabs Flash$4020× more
ElevenLabs Multilingual$8040× more
1 million characters a month

$2others average $31

10 million characters a month

$20others average $308

100 million characters a month

$200others average $3,075

List prices per million characters from each company's public pricing page, checked on 15 November 2026: OpenAI tts-1; Deepgram Aura-2, pay as you go; Cartesia Sonic, Scale plan overage; ElevenLabs Flash / Turbo and Multilingual v2. "Others average" is the mean of OpenAI tts-1, Deepgram Aura-2, Cartesia Sonic and ElevenLabs Flash. Plans, models and discounts change, so check their pages for today's price. All names belong to their owners.

The API

A few lines of code. Then it talks.

Post your text to one endpoint and the audio starts coming back while the rest is still being made. Nothing to install and nothing new to learn.

  • Streams as you writeREST or WebSocket. Feed it your language model's reply as the words arrive.
  • Ready for phone linesOpus, WAV, μ-law, A-law or raw PCM, picked per request.
  • Any pace you likeFrom 0.6× to 1.8×, at 24 kHz.
  • Says numbers properlyAmounts, dates, phone numbers and acronyms, read the way a person would.
curl -sN -X POST "$QUICK_TTS_URL/v1/tts" \
  -H "x-api-key: $QUICK_TTS_KEY" \
  -H "content-type: application/json" \
  -d '{"text":"Your table for four is confirmed for eight tonight.",
       "voice":"kiara","format":"wav"}' \
  -o hello.wav
200 · audio/wavaudio arriving

Your endpoint and key arrive with your pilot.

10 s

to make a full minute of speech

20

live conversations on one four-core server

25×

faster than real time, per server

Measured on one four-core cloud server on 3 November 2026, with paragraph-length text and no gaps in playback. We publish below what we measure, so there is headroom on every figure.

Apply for a pilot

Run it on your own traffic.

Tell us what you are building. You get an endpoint and a key, and you hear the difference on your own requests.

  1. Tell us the jobWhat it will say, and roughly how much.
  2. Get your keyWe reply by email with an endpoint, a key and a quickstart.
  3. Compare for yourselfPut it beside the voice you pay for today.

Your message goes straight to the two founders.

We use your details only to reply. Privacy

In pilot

Already answering for PlatterHub.

Our first pilot partner puts the voice in front of real brands and creators. The next places are open now.

Apply for a pilot
Pilot partnerMarketing platform
PlatterHub
Brands & creatorsinfluencer campaigns, answered by voice

PlatterHub runs influencer campaigns for brands. Our voice answers its brands and creators: campaign questions, onboarding and support, spoken, not ticketed.

platterhub.ai
AgentBox Coming soon

Next: the whole call, answered for you.

AgentBox is a voice agent for your website and your phone line, built on the same voices and the same engine. It listens, gets the job done in your systems and hands over to a person when it should.

  • Web and phone
  • Runs on Quick TTS
  • Hands over to your team
Ask about early access
Questions

Straight answers.

Anything missing? Ask in the pilot form and a founder will reply.

What is Quick TTS?

A text-to-speech API built on our own voice model and our own engine. You send text over REST or WebSocket and natural US English speech comes back while it is still being generated.

How much does it cost?

$2 per million characters, which works out at about 0.2¢ for a minute of speech. There are no seats, no setup fee and no charge per stream.

Why is it so much cheaper?

We trained the model and wrote the engine ourselves, and it runs on ordinary CPU servers. There is no model vendor or GPU bill in the middle, so the saving goes to you.

How fast is it?

The first audio leaves our server 11 to 64 milliseconds after your text arrives, and a full minute of speech takes about ten seconds to make.

Which voices can I use?

Eighteen US English voices at 24 kHz, with the pace set anywhere from 0.6× to 1.8× on each request. You can try them in the playground on this page.

Does it read numbers, amounts and dates correctly?

Yes. Currency amounts, dates, phone numbers and acronyms are read the way a person would say them.

How many calls can it handle at once?

One four-core server carries 20 live streams. Capacity grows by adding servers, and a stream that has started is never cut short.

Can it run 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 where it is.

Can you make a custom voice for my brand?

Yes. We need about thirty minutes of clean studio audio, with the speaker's consent on record, and two to three weeks. It costs the same per character and runs at the same speed.

How do I start?

Apply for a pilot. We reply by email with an endpoint, a key and a short quickstart.