GPT-Live 1 speaks in a voice you describe
GPT-Live 1 now speaks in a voice you describe
OpenAI's voice model, GPT-Live 1, can now speak in a voice you invent. You describe the voice in a sentence, and you can reuse it. Every API customer has it as of October 16th, along with nine new voices.
Voices from a description
GPT-Live 1Voices from a description.
Describe it, get a saved voice
GPT-Live 1Write the voice as a sentence and get back a saved voice
“A calm, reassuring adult voice for a customer support assistant. Speak with an American English accent, a mid-range pitch, a smooth, warm tone, and a steady, conversational pace.”
You describe the voice in plain words: its accent, age, pitch, tone and pace. Send that through the API or the voice Playground, and you get back an ID to reuse in any GPT-Live session. No recording is needed.
Creating a voice is free
GPT-Live 1Speaking in it is billed as a regular GPT-Live session.
Making a voice costs nothing. You pay when it talks, at the normal GPT-Live session rate. Listening to a voice in the Playground also counts as a session.
GPT-Live only
GPT-Live 1Voices made from a description work in GPT-Live only
These voices speak inside GPT-Live sessions. The Text to Speech, Realtime and Chat Completions APIs don't accept them, so an app built on text to speech can't switch to one yet.
Adult voices, never imitations
GPT-Live 1Adult voices, described rather than imitated
Every voice has to sound like an adult. A description can't ask for a named person, a public figure or a fictional character. And your listeners must be told the speech is AI-generated.
A hundred voices per organization
GPT-Live 1Up to 100 voices per organization
An organization can make up to 100 voices, counting the ones your app creates for its own customers. Voice creation doesn't work under Zero Data Retention. Cloning a voice from a recording stays limited to eligible customers.
Nine new voices
GPT-Live 1Nine new voices.
Nine natural voices in five languages
GPT-Live 1Nine natural voices join GPT-Live, speaking German, French, Hindi, Japanese and Korean. German gets three, French and Japanese two each, and Hindi and Korean one. You pick the voice when a session starts.
What GPT-Live 1 is
GPT-Live 1What GPT-Live 1 is.
Listens and speaks at once
GPT-Live 1GPT-Live 1 listens and speaks at the same time
GPT-Live 1 is OpenAI's model for spoken conversation. It listens while it talks, so a caller can interrupt or add a detail mid-sentence. It takes audio and text, and answers in both.
A backend agent does the work
GPT-Live 1A backend agent does the reasoning while GPT-Live keeps talking
GPT-Live hands lookups and tool calls to a backend agent, and keeps talking with the caller until the result arrives. OpenAI can run that backend for you, or you connect your own agent.
Five cents a minute
GPT-Live 1$0.05 a minute, billed by the second
The backend model and its tools are billed separately.
A GPT-Live session costs five cents a minute, counted by the second and never rounded up to a whole minute. The backend model and its tools are billed on top.
Who can use it
GPT-Live 1In the API since September 10, with no free tier
GPT-Live 1 has been generally available in the API since September 10th. The free tier can't use it. Paid tiers are limited by concurrent sessions, from 50 on Build to 500 on Grow.
Make your first voice
GPT-Live 1Make your first voice with OpenAI’s Custom voices guide
developers.openai.com › GPT-Live › Custom voices
To make your first voice, OpenAI's Custom voices guide has the request and example descriptions to start from. It's on OpenAI's developer site, under GPT-Live.
