API Plan Finder
Prices and limits match the providers' official pagesChecked 2026-10-18

Speech-to-text API

OpenAI Speech to Text

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
Plans recorded
2
Checked
2026-10-17 – 2026-10-18
Pricing page
developers.openai.com/api/docs/pricing.md

Plans

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

PlanPriceIncludedExtra usageConcurrencyRate limitBuy
whisper-1, recorded audio (pay as you go)Pay as you go
Transcription of recorded audio: Yes3
Real-time streaming speech: Not stated4
$360 per 1,000 audio hours56
 Not recorded
$360 per 1,000 extra57
Not recorded
Not recorded
 Pricing pageChoose the plan on the page
gpt-live-transcribe, live audio (pay as you go)Pay as you go
Real-time streaming speech: Yes8
Transcription of recorded audio: Not stated9
$1,020 per 1,000 audio hours1011
 Not recorded
$1,020 per 1,000 extra1012
Not recorded
Not recorded
 Pricing pageChoose 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)
EU12

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

    developers.openai.com/api/docs/guides/your-data.md · official docs · read 2026-10-17

  2. 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.

  3. Files can be up to 25 MB.

    developers.openai.com/api/docs/guides/speech-to-text.md · official docs · read 2026-10-17

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

  5. | Cost | $0.006 | minute |

    developers.openai.com/api/docs/models/whisper-1.md · official pricing · read 2026-10-17

  6. 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.

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

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

    developers.openai.com/api/docs/guides/realtime-transcription.md · official docs · read 2026-10-17

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

  10. | gpt-live-transcribe | Live transcription | - | - | $0.017 / minute |

    developers.openai.com/api/docs/pricing.md · official pricing · read 2026-10-17

  11. 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.

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

Check these plans against your workload JSON