# OpenAI Speech to Text plans, limits and prices

Speech to text over the transcription API for recorded audio (whisper-1) and the realtime API for live audio (gpt-live-transcribe), billed per minute of audio.

- Provider: OpenAI
- Kinds: Speech-to-text API
- Plans recorded: 2
- Checked: 2026-10-17 – 2026-10-18
- Page for people: https://plans.intoperson.com/p/openai-transcription

## Plans

Values that apply to one plan. "Not stated" means the official pages do not say; it is not an estimate.

### whisper-1, recorded audio (pay as you go)

Plan id: `openai-stt-whisper` · Pay as you go

- Price: $360 per 1,000 audio hours [1][2]
- Included: Not recorded
- Extra usage: $360 per 1,000 extra [1][3]
- Concurrency: Not recorded
- Rate limit: Not recorded
- Transcription of recorded audio: Yes [4]
- Real-time streaming speech: Not stated [5]
- Visit: [Pricing page](https://plans.intoperson.com/go/openai-stt-whisper) (choose the plan on the page)

### gpt-live-transcribe, live audio (pay as you go)

Plan id: `openai-stt-live` · Pay as you go

- Price: $1,020 per 1,000 audio hours [6][7]
- Included: Not recorded
- Extra usage: $1,020 per 1,000 extra [6][8]
- Concurrency: Not recorded
- Rate limit: Not recorded
- Real-time streaming speech: Yes [9]
- Transcription of recorded audio: Not stated [10]
- Visit: [Pricing page](https://plans.intoperson.com/go/openai-stt-live) (choose the plan on the page)

## Applies to every plan

Recorded for the product or the provider; a plan-level value or a listed exception replaces it.

- Data storage or processing region (all products): EU [11][12]

## Collection notes

Pay as you go only. The two plans are the model lines with a per-minute price in the "Estimated cost" column and no token price: whisper-1 for recorded audio ($0.006 a minute) and gpt-live-transcribe for live audio ($0.017 a minute). The token-billed models (gpt-4o-transcribe, gpt-4o-mini-transcribe, gpt-4o-transcribe-diarize) show only an estimated per-minute cost next to token prices and are not modelled. The MCP server is the documentation MCP server: it searches and reads the developer docs and has no transcription tools.

## Sources and notes

Each number points to the provider's own sentence, as it appears on the page on the date shown.

1. [developers.openai.com/api/docs/models/whisper-1.md](https://developers.openai.com/api/docs/models/whisper-1.md) · official pricing · read 2026-10-17

> | Cost | $0.006 | minute |

2. How the value follows from the source: $0.006 per audio minute x 60 = $0.36 per audio hour, so $360 per 1,000 audio hours.

3. How the value follows from the source: $0.006 per audio minute x 60 x 1,000.

4. [developers.openai.com/api/docs/guides/speech-to-text.md](https://developers.openai.com/api/docs/guides/speech-to-text.md) · official docs · read 2026-10-17

> Files can be up to 25 MB.

5. This price line is for audio files; live audio is the realtime plan (gpt-live-transcribe).

6. [developers.openai.com/api/docs/pricing.md](https://developers.openai.com/api/docs/pricing.md) · official pricing · read 2026-10-17

> | gpt-live-transcribe | Live transcription | - | - | $0.017 / minute |

7. How the value follows from the source: $0.017 per audio minute x 60 = $1.02 per audio hour, so $1,020 per 1,000 audio hours.

8. How the value follows from the source: $0.017 per audio minute x 60 x 1,000.

9. [developers.openai.com/api/docs/guides/realtime-transcription.md](https://developers.openai.com/api/docs/guides/realtime-transcription.md) · official docs · read 2026-10-17

> Use realtime transcription when your application needs text from a microphone, call, or other live audio stream without a spoken assistant response.

10. This price line is for live audio; recorded audio is the whisper-1 plan.

11. [developers.openai.com/api/docs/guides/your-data.md](https://developers.openai.com/api/docs/guides/your-data.md) · official docs · read 2026-10-17

> | Europe (EEA + Switzerland) | `eu.api.openai.com` | Yes | Yes | Yes\*\* | Text, Audio, Voice, Image\* | `/v1/audio/transcriptions, /v1/audio/translations, /v1/audio/speech`

12. The EU row of the data residency table lists the transcription endpoint. The table lists other regions, which are not entered, and regions other than the United States need approval and a modified retention amendment.

Check these plans against a workload: https://plans.intoperson.com/guide.md describes the inputs; the REST form is GET https://plans.intoperson.com/api/v1/products/openai-transcription.