GPT Transcribe

OpenAI's speech-to-text model for completed audio, billed per minute. Served through the gateway's /v1/realtime WebSocket endpoint as a transcription session (intent=transcription) or as the input-audio transcription model of a speech-to-speech session, transcribing each turn once its audio is committed.

gpt-transcribe
BETAGet StartedView uptime
0 context
Released July 28, 2026
Starting at $0.00/M input tokens
Starting at $0.00/M output tokens
No ratings yetSign in to rate

Select Provider

All Providers for GPT Transcribe

LLM Gateway routes requests to the best providers that are able to handle your prompt size and parameters.

Context:
Audio Transcription Pricing
Input audio$0.27/hour
Get Started

Frequently asked questions

What is GPT Transcribe?

OpenAI's speech-to-text model for completed audio, billed per minute. Served through the gateway's /v1/realtime WebSocket endpoint as a transcription session (intent=transcription) or as the input-audio transcription model of a speech-to-speech session, transcribing each turn once its audio is committed. You can access it through LLM Gateway's OpenAI-compatible API with automatic provider routing, fallback, and cost analytics.

How much does GPT Transcribe cost?

Pricing for GPT Transcribe on LLM Gateway starts at $0.00 per million input tokens and $0.00 per million output tokens, depending on the provider. The pricing table above always reflects the current per-provider rates.

Which providers serve GPT Transcribe?

GPT Transcribe is served by OpenAI through LLM Gateway. Requests are automatically routed to the best available provider, with fallback when a provider has issues.

Does GPT Transcribe support tool calling and structured outputs?

No. GPT Transcribe does not currently support tool calling or structured JSON outputs through LLM Gateway.

When was GPT Transcribe released?

GPT Transcribe was released on July 28, 2026.