GPT Transcribe is OpenAI's speech to text model. A speech-to-text ASR model for transcribing completed audio files and streamed sessions, with support for keyword hints and unstructured context.
Specifications
Canonical IDopenai-gpt-transcribe
TypeSpeech to Text
StatusActive
CreatorOpenAIOpenAI
Providers
Input ModalitiesAudioText
Output ModalitiesText

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
OpenAI logo
OpenAI
gpt-transcribe
$0.000075

Cost Calculator

US Dollar ($)
Preset:

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
GPT-5.6 Sol1.1M$2.50$15.00Deprecating
GPT-5.6 Terra1.1M$1.00$6.00Deprecating
GPT-5.6 Luna1.1M$0.100$0.600Deprecating
GPT-5.51.1M$2.50$15.00Available
GPT-5.4 Mini400K$0.375$2.25Deprecating
GPT-5.4 Nano400K$0.100$0.625Deprecating
GPT-5.41.1M$1.25$7.50Deprecating
GPT-5.3 Codex400K$1.75$14.00Deprecating
GPT-5.2 Codex400K$1.75$14.00Deprecated
GPT-5.2410K$0.875$7.00Deprecating
GPT TranscribeCurrent

Model IDs

gpt-transcribe
openai-gpt-transcribe