What Uttera is

Uttera works with audio. You give it recorded voice and it hands back text, analysis or more voice; you give it text and it hands back speech, sound effects or music.

It is built for what happens after a recorded conversation — a call, a meeting, an interview, a voice note: transcribing it, knowing who spoke and in what tone, translating it or summarizing it. It is not a text translator or a document reader: audio is at one end or the other, always.

And for anyone cutting video or podcasts, what is missing once the voice is done: sound effects and music, described in words and generated on the spot. With a clear licence and no catalogue to dig through.

Ways to use it

You don't need to know how to program to use Uttera. There are several doors, and most people only need the first:

Studio

A TTS/STT web application. You upload a file, tick what you want and download the result. Nothing to install and not a line of code. How to use it.

Pronounce

The second web application, and deliberately much narrower: you write a sentence, hear it in the language you are learning, and say it yourself so we can tell you which sound went wrong. How to use it.

Sounds

Describe a sound and get a clip; describe a whole scene and get it broken into events you can fix before generating them. How to use it.

Music

Describe the music you need and get a finished piece, up to six minutes long. You choose how long it runs and how much quality you want. How to use it.

Self-hosted

The voice engines are open source and live on GitHub: transcribing and speaking, each in two variants. You download them, run them on your own machine and the audio never leaves your network. It is the engine, not the platform: the applications and the other services live here.

The API

So your own software can talk to ours: putting Uttera inside your phone system, your CRM or your application, so the work happens on its own, with nobody uploading files by hand. How to use it.

Working with an AI agent? You don't need to read this and relay it. Tell it

read https://uttera.ai/skill.md and follow the
instructions

and it sets itself up: checks your key, learns the endpoints and warns you what things cost. It cannot sign you up —that is on you, deliberately— but it can get everything ready with a key you already have.

The applications and the API do exactly the same thing and cost exactly the same: none of them is a cut-down version or a demo, they are the same machine with a button in front. The only difference is who presses the button — a person or a program.

If you want to see at a glance what is behind each door, it is laid out in what you can do with Uttera.

What is an API?

API stands for Application Programming Interface. Without the jargon: it is the door through which one program asks another program for something.

The comparison that works best is a restaurant. You don't walk into the kitchen: you tell the waiter what you want, they take it inside and come back with the dish. You don't need to know how the kitchen is laid out, which oven they use, or how many cooks there are. You only need to know what you can order and how to order it. The API is the waiter, and this documentation is the menu.

In practice, a program of yours sends an audio file over the internet to an address of ours, along with a key that says who you are, and gets the result back. Nothing is installed on your computer: the work happens on our machines and only the request and the response travel.

If you're never going to write code, you can skip everything about the API and go straight to the Studio. This documentation describes both doors, but the first one requires nothing technical.

The name

Uttera /ˈʌt.ər.ə/ comes from the English verb to utter: to pronounce, to say aloud, to give audible expression to something.

Formally it is also a backronym of Universal Text Transformer Engine for Realtime Audio, which captures its origin — a speech-to-text and text-to-speech server — and the Transformer architecture it is built on.

What it can do

Transcribe

Audio → text, with automatic language detection.

Text to speech

Text → audio, from a voice catalog.

Translate

Audio in one language → text and speech in another.

Analyze the voice

Tone and speaker profile: apparent age, accent, mood.

Know who is speaking

Who says what, and at what minute. A meeting of six comes back split by speaker.

Summarize

A whole recording → structured summary.

Sound effects

Text → one clip, or a whole scene laid out in time.

Music

Text → a finished piece, up to 6 min 20 s.

Signed report

A recording → a PDF a third party can verify on their own, without taking our word for it.

Concepts

Credits

Everything is billed in credits. One credit is one second of GPU time, and each service has its coefficient according to what it actually consumes. There are no per-request charges and no minimums: you pay by second of audio processed or generated.

Your plan gives you a monthly allowance of credits that renews on your subscription date, not on the 1st of the month. What you don't spend does not carry over.

Voices

There are two families. The standard voices are a fixed catalog, fast and cheap. The cloned voice reproduces a particular timbre from a sample, costs about 19 times more per second, and is not in every plan.

Duration, not size

Billing goes by seconds of audio, not by megabytes. The same minute of speech costs the same in WAV as in MP3, even though the file is twenty times heavier.

Your first request

You need a key. You create it in your account; it starts with sk-echo- and is shown only once.

curl -X POST https://api.uttera.ai/v1/audio/transcriptions \
  -H "Authorization: Bearer $UTTERA_API_KEY" \
  -F file=@recording.mp3 \
  -F model=whisper-1 \
  -F response_format=text

Response:

Good morning, I was calling about last week's order...

Tip: if you'd rather not write code yet, the Studio runs the services from your browser and shows you what each one costs before and after you launch it.