An AI voice generator that ships to production.

Generators demo well and then meet production. This one is the production endpoint — the specimens below came out of it, dated, and the same request works from your backend tonight.

marginal cost of a busy month

Fig. 0 — voice specimens · pre-rendered on the production API

generated 2026-07-16

Leo
English
“I've placed a temporary hold on the card ending four two one nine after two charges that don't fit your pattern. If those were you, I can lift it right now. If not, I'll have a new card on its way before we hang up.”
financial services · fraud hold
11.3 s
Jenny
English
“You're all set for Thursday at ten with Doctor Okafor. I've texted the address and the two intake forms — reply here anytime and I'll move the appointment if something comes up.”
healthcare · appointment line
10.3 s
Mia
English
“Good news — your refund went through this morning, and the confirmation number is already in your inbox. It usually settles back to your card within two business days. Anything else I can take care of?”
retail · returns desk
10.4 s
Dane
English
“Your balance is about thirty days past due, and I'd much rather work it out with you than let it escalate. I can split it into two payments — would the first one landing this Friday work for you?”
collections · payment plan
9.4 s
Lewis
English
“I've opened the claim for the water damage and assigned it to an adjuster — they'll reach out within one business day. Hold on to the photos you took; they'll move everything along faster.”
insurance · first notice of loss
9.4 s
Ava
English
“Good morning, and thank you for calling the front desk. I can check you in, arrange a late checkout, or book you a table for tonight — what would help you most right now?”
hospitality · front desk
8.7 s
Dane
English
“Driver twelve is eight minutes out with two pallets, and dock four is clear. I've dropped the manifest in your inbox so you can check it before they pull in.”
logistics · dispatch
7.0 s
Leo
English
“Your technician is booked for Tuesday between nine and eleven. I'll send a text when they're about thirty minutes out, so you're not stuck waiting around all morning.”
field service · scheduling
7.7 s
Dane
English
“Ondansetron twice daily; the subpoena arrived Thursday; the charcuterie is from Worcestershire.”
hard words, first try
5.6 s

Stock voices, ready-made on the API — six of them, all multilingual. Cloning from ten seconds of your own voice runs on the call.

From play button to production

The gap between a demo and a deploy is usually a different endpoint. Here it is the same one: what you hear on this page is what your product ships.

the same generation, from your backend

import base64, requests

ref = base64.b64encode(open("brand.wav", "rb").read()).decode()

audio = requests.post(
    "https://tts.gandr.ai/v1/tts/bytes",
    headers={"x-api-key": "gnd_yourkey"},
    json={
        "transcript": "This page and your product"
                      " ship the same audio.",
        "voice": {"mode": "clone", "wav_b64": ref},
        "output_format": {"sample_rate": 24000},
    },
).content

open("line.wav", "wb").write(audio)

Six voices stocked, any voice by reference

Six multilingual stock voices ship ready-made — pick one and generate. And the library is also whatever you can record: about ten seconds of any consenting speaker becomes the voice of the request. Brand voice, founder voice, one voice per market — each is a clip, not a project.

What it costs to generate a lot

Nothing marginal. Generation is unmetered on a line — $150 a month flat — so a busy month of synthesis costs what a quiet one does. Below about 5,000 spoken minutes a month, a metered vendor is cheaper and we say so.

Notes — an engineer's checklist

01Is there a web studio or is it API-only?

The console on the home page speaks the production API in the browser — type a line, hear it back. Everything else is the API itself, because the product is the endpoint, not an editor.

02Can I generate long-form audio?

Requests cap at 2,000 characters per utterance — call-sized on purpose. Long-form work is a loop over utterances, and since characters are unmetered the loop costs nothing marginal.

03Are the specimens on this page edited?

No — they are dated, ungated output of POST /v1/tts/sse, published as generated. The same discipline as the latency figures: what you can check is what we claim.

Related sheets.

capability

Voice cloning from ten seconds, in the request

Zero-shot voice cloning: a ten-second reference rides inside each request, no training job, and the identity holds across 23 languages.

capability

A text-to-speech API built for live calls

REST, SSE, and WebSocket TTS from one endpoint: 107 ms measured first audio, instant cloning from ten seconds, flat per-line pricing with unmetered characters.

glossary

$30–$100

TTS pricing: per character vs flat rate

The two ways speech synthesis is priced, what each one does to a voice product, and which side of the break-even your workload sits on.

Your script, this API, thirty minutes — and the recording leaves with you.

Hear it on your own script