Sign up
All models
OpenAI

gpt-live-transcribe

Try in Playground

GPT Live Transcribe turns incoming speech into text, not spoken replies. Here it can be selected for input transcription within a /v1/realtime conversation when the key permits it and a separately priced route is available. It is billed by audio duration, not chat tokens.

The real OpenAI model

Same weights, same API, same answers. We change only how you pay for it: one key for every maker, one bill, no separate account to open. Every figure on this page comes from OpenAI’s own page — check it.

Price

per minute

Input

Output

$0.00

$0.02

Modalities

How it is served

Standard

Requests are retried automatically if a provider is unavailable.

Similar models

Models built for the same kind of work, at a similar price.

OpenAI
openai/gpt-realtime-whisper$0.00 / $0.02

We do not mark up the price of tokens. It is the same price the maker charges.

Use it from your code

Model:openai/gpt-live-transcribe
main.py
OpenAI Specification v1.0
from openai import OpenAI

# Works with the official openai package (pip install openai)
client = OpenAI(
    base_url="https://api.flintbeam.com/v1",
    api_key="sk-live-your-api-key"
)

response = client.chat.completions.create(
    model="openai/gpt-live-transcribe",
    messages=[
        {"role": "system", "content": "You are an experienced software engineer."},
        {"role": "user", "content": "Describe the architecture of a distributed cache."}
    ],
    temperature=0.7,
    max_tokens=1500
)

print(response.choices[0].message.content)