GPT Live Transcribe is OpenAI's speech to text model with a 32K context window and up to 4K output tokens, available from 2 providers. A streaming speech-to-text ASR model designed for low-latency live audio transcription with support for keyword hints and tunable latency.
Specifications
Canonical IDopenai-gpt-live-transcribe
TypeSpeech to Text
StatusActive
CreatorOpenAIOpenAI
Providers
Context Window32K tokens
Max Output4K tokens
Input ModalitiesAudioText
Output ModalitiesText
Deprecation Date

Capabilities

Input2/5
Text✓
Image·
Audio✓
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities0/13
Reasoning·
Adaptive Reasoning·
Function Calling·
Parallel Function Calling·
Structured Outputs·
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·

Pricing by Provider

US Dollar ($)
Per 1M tokens
ProviderStandard
Audio In
$ / sec
Azure AI Foundry logo
Azure AI Foundry
azure/gpt-live-transcribe
$0.000283
OpenAI logo
OpenAI
gpt-live-transcribe
$0.000283

Cost Calculator

US Dollar ($)
Preset:

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
GPT-6.1 Sol1.1M$2.00$10.00Available
GPT-6 Sol1.1M$2.00$10.00Available
GPT-6 Luna1.1M$0.100$0.500Available
GPT-6 Astra1.1M$10.00$50.00Available
GPT-5.6 Sol1.1M$2.00$10.00Available
GPT-5.6 Terra1.1M$2.00$12.00Available
GPT-5.6 Luna1.1M$0.200$1.20Available
GPT-5.51.1M$5.00$30.00Available
GPT-5.4 Mini400K$0.750$4.50Available
GPT-5.4 Nano400K$0.200$1.25Deprecating
GPT Live Transcribe—32K——Current

Model IDs

azure/gpt-live-transcribe
gpt-live-transcribe
openai-gpt-live-transcribe