# GPT Transcribe

GPT Transcribe is a speech-to-text model from OpenAI, available through the Impossibl API. The advertised input rate is $0.0045 per minute of audio.

- Model identifier: ` openai/gpt-transcribe `
- Creator: OpenAI
- Model type: Speech to text
- Canonical model page: [GPT Transcribe](<https://impossibl.com/openai/gpt-transcribe>)
- API availability: Listed as serving through Impossibl.
- Creator release date: 2026-07-28

## Capabilities and limits

- Context window: Not published
- Maximum output tokens: Not published in the public catalog; this is separate from the context window.
- Inputs: audio, text
- Outputs: text
- Tool calling: Not published

## API access

Use ` openai/gpt-transcribe ` as the model identifier through the Impossibl API.

Published API endpoints:

- ` /v1/audio/transcriptions `

[API quickstart](<https://impossibl.com/docs/agent-quickstart>) · [Models and billing documentation](<https://impossibl.com/docs/models>)

## Published API prices

All rates are in USD. An unpublished rate is unknown, not zero. Workspace-specific pricing, taxes, balance-purchase fees, billing adjustments, and tool charges can affect the amount paid.

| Usage | Published base rate | Billing unit |
| --- | --- | --- |
| Input | $0.0045 | per minute of audio |

## Independent benchmarks

Source: [Artificial Analysis](<https://artificialanalysis.ai/>). Last checked: 2026-09-11T10:19:11.718Z.
Configurations are evaluated separately. API scores retain their original units. Unmeasured scores are omitted.

### GPT Transcribe, OpenAI (speech-to-text)

Source: [Evaluation source](<https://artificialanalysis.ai/api/v2/media/speech-to-text/models/free>)

| Benchmark | Score |
| --- | --- |
| Word Error Rate Index | 0.00 |

Full benchmark data and breakdowns: [Complete benchmark snapshot](<https://api.impossibl.com/v1/models/openai/gpt-transcribe/benchmarks>).


## Availability and retirement

The model is listed as serving. No retirement is announced in the current public catalog.

## Frequently asked questions

### What is GPT Transcribe?

GPT Transcribe is a speech-to-text model from OpenAI, available through the Impossibl API.

### How much does GPT Transcribe cost?

GPT Transcribe costs $0.0045 per minute of audio through the Impossibl API. All rates are in USD.

### What inputs and outputs does GPT Transcribe support?

GPT Transcribe accepts audio and text as input. GPT Transcribe returns text.

### How do I use GPT Transcribe through an API?

GPT Transcribe is available through the Impossibl API. Use openai/gpt-transcribe as the model identifier with /v1/audio/transcriptions. The quickstart explains how to create an API key and send your first request.

### When was GPT Transcribe released?

OpenAI released GPT Transcribe on July 28, 2026.

Sources: [Creator release announcement](<https://developers.openai.com/api/docs/changelog>)

## Sources and related links

Prices, limits, capabilities, endpoints, and availability come from the public Impossibl catalog. Creator documentation supplies descriptions and release dates where available; it does not override the published API offering.

- [Public Impossibl model catalog](<https://api.impossibl.com/v1/models>)
- [Full model directory as JSON](<https://impossibl.com/models.json>)
- [GPT Transcribe: model details and pricing](<https://impossibl.com/openai/gpt-transcribe>)
- [Model directory](<https://impossibl.com/models>)