impulse

GPT Live Transcribe

Frontier labTranscription
API id gpt-live-transcribe
Input / 1M
-
not listed
Output / 1M
-
not listed
Context window
32K
tokens
Max output
4K
tokens per reply
Hosts
2
2 listings
Released
-
date not published

Where to run it

2 hosts serve GPT Live Transcribe. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
OpenAILab API
gpt-live-transcribe
-
gpt-live-transcribe
-
Retires 1 Feb 2028

Capabilities

Core

  • Streaming
  • Function calling
  • JSON mode
  • Structured outputs

Multimodal

  • Vision
  • Image input
  • Audio
  • Image generation
  • Video

Advanced

  • Reasoning
  • Tool calling
  • MCP
  • Prompt caching
  • Batch API
  • Embeddings
Takes in
AudioText
Produces
Text
Features
Audio input

Similar models

This model has no listed price, so these are current models with similar capabilities.

Smaller OpenAI models

No similar OpenAI model keeps its key capabilities.

Other frontier labs

Open-weight picks

No similar open-weight match.

Call it

Using OpenAI's API.

Python
from openai import OpenAI

client = OpenAI()  # reads OPENAI_API_KEY

response = client.responses.create(model="gpt-live-transcribe", input="Hello")
print(response.output_text)

Quick answers

Which APIs offer GPT Live Transcribe?

GPT Live Transcribe runs on 2 APIs: OpenAI and Azure OpenAI.

What is GPT Live Transcribe's context window?

32K tokens, with up to 4K tokens in one reply.

Is GPT Live Transcribe being retired?

Azure OpenAI retires it on 1 Feb 2028. 1 host keeps serving it.

What is GPT Live Transcribe's API model id?

Use gpt-live-transcribe with OpenAI.

Sources

Raw catalog entry for gpt-live-transcribe on OpenAI
{
  "input_cost_per_second": 0.000283333333333,
  "litellm_provider": "openai",
  "mode": "audio_transcription",
  "source": "https://developers.openai.com/api/docs/pricing",
  "supported_endpoints": [
    "/v1/realtime",
    "/v1/realtime/transcription_sessions"
  ],
  "supported_modalities": [
    "text",
    "audio"
  ],
  "supported_output_modalities": [
    "text"
  ],
  "supports_audio_input": true,
  "supports_native_streaming": true
}