# OpenAI Whisper (API) Review

> OpenAI Whisper (API) review: Low-cost pay-as-you-go file transcription from OpenAI; no first-party streaming or diarization. Verified pricing, features, and.

![OpenAI Whisper (API) logo](https://www.versusref.com/logos/whisper.png)

Low-cost pay-as-you-go file transcription from OpenAI; no first-party streaming or diarization

Among the 43 speech-to-text tools we track, OpenAI Whisper (API) has the 21st-widest language coverage.

See pricing · facts verified Jul 20, 2026

## What we know about OpenAI Whisper (API)

OpenAI Whisper (API) sits in the speech-to-text apis category, where it is low-cost pay-as-you-go file transcription from OpenAI; no first-party streaming or diarization. We keep this OpenAI Whisper (API) profile grounded in primary sources, each fact dated to when we last confirmed it.

OpenAI Whisper (API) does not publish a public per-minute rate we have been able to verify, so the price figure here stays blank until we can confirm one. We would rather show nothing than a guessed number; if you have a current OpenAI Whisper (API) quote, it is the fastest way for us to close that gap.

On capabilities, OpenAI Whisper (API) covers language auto-detection, word-level timestamps, custom vocabulary / keyterm boosting, speech translation, soc 2 type ii, and gdpr / eu data residency, and does not offer entity detection, sentiment analysis, and summarization endpoint. Each of those is verified against OpenAI Whisper (API)'s own docs or dashboard, not marketing copy.

For compliance, with OpenAI Whisper (API): SOC 2 Type II is in place. If you are in a regulated space, confirm the current posture with OpenAI Whisper (API) before you commit, since these change plan by plan.

OpenAI Whisper (API) ranks the 21st-widest language coverage of the 43 speech-to-text tools we track, so where it lands for you depends on which of those matters more.

In total we track 23 verified facts for OpenAI Whisper (API) today, each linking the primary source it came from so you can check our work - and vendor claims we have not measured ourselves are labeled as such on the OpenAI Whisper (API) fact sheet below.

## OpenAI Whisper (API) pricing

Published rates: batch $0.006/min, verified Jul 20, 2026 ([source](https://developers.openai.com/api/docs/models/whisper-1)).

| Monthly volume | Monthly bill (batch) |
| --- | --- |
| 1K min/mo | $6 |
| 10K min/mo | $60 |
| 100K min/mo | $600 |

Sticker rates only; diarization and PII redaction add-ons price in the stack builder.

## Fact sheet

### Pricing

| Fact | Value | Verified | Source |
| --- | --- | --- | --- |
| Batch price per audio minute | 0.006 $/audio-min | Jul 20 | [source](https://developers.openai.com/api/docs/models/whisper-1) |
| Pricing model | usage | Jul 20 | [source](https://developers.openai.com/api/docs/pricing) |
| Concurrency on base plan | Tier 1: 500 RPM; scales to 10,000 RPM at Tier 5 | Jul 20 | [source](https://developers.openai.com/api/docs/models/whisper-1) |

### Capabilities

| Fact | Value | Verified | Source |
| --- | --- | --- | --- |
| WER (third-party benchmark) | 4.06 % WER | Jul 20 | [source](https://artificialanalysis.ai/speech-to-text) |
| Languages supported | 57 languages | Jul 20 | [source](https://developers.openai.com/api/docs/guides/speech-to-text) |
| Language auto-detection | ✓  Yes | Jul 20 | [source](https://developers.openai.com/api/docs/models/whisper-1) |
| Speaker diarization | ✗  Not available | Jul 20 | [source](https://developers.openai.com/api/docs/guides/speech-to-text) |
| PII redaction | ✗  Not available | Jul 20 | [source](https://developers.openai.com/api/docs/api-reference/audio/createTranscription) |
| Word-level timestamps | ✓  Yes | Jul 20 | [source](https://developers.openai.com/api/docs/api-reference/audio/createTranscription) |
| Custom vocabulary / keyterm boosting | ✓  Yes | Jul 20 | [source](https://developers.openai.com/api/docs/guides/speech-to-text) |
| Entity detection | ✗  No | Jul 20 | [source](https://developers.openai.com/api/docs/api-reference/audio/createTranscription) |
| Sentiment analysis | ✗  No | Jul 20 | [source](https://developers.openai.com/api/docs/api-reference/audio/createTranscription) |
| Summarization endpoint | ✗  No | Jul 20 | [source](https://developers.openai.com/api/docs/guides/speech-to-text) |
| Speech translation | ✓  Yes | Jul 20 | [source](https://developers.openai.com/api/docs/guides/speech-to-text) |

### Compliance & trust

| Fact | Value | Verified | Source |
| --- | --- | --- | --- |
| HIPAA BAA available | ✓  Yes | Jul 20 | [source](https://developers.openai.com/api/docs/guides/your-data) |
| SOC 2 Type II | ✓  Yes | Jul 20 | [source](https://trust.openai.com/) |
| GDPR / EU data residency | ✓  Yes | Jul 20 | [source](https://developers.openai.com/api/docs/guides/your-data) |
| Self-host / on-prem option | ✗  No | Jul 20 | [source](https://developers.openai.com/api/docs/guides/speech-to-text) |
| Model weights license | MIT | Jul 20 | [source](https://github.com/openai/whisper) |

### Build experience

| Fact | Value | Verified | Source |
| --- | --- | --- | --- |
| Official SDKs | Python, JS/TS, .NET, Ruby, Java (beta), Go (beta) | Jul 20 | [source](https://developers.openai.com/api/docs/libraries) |
| Max file size / duration | 25 MB max upload per request | Jul 20 | [source](https://developers.openai.com/api/docs/guides/speech-to-text) |
| Supported audio formats | flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, webm | Jul 20 | [source](https://developers.openai.com/api/docs/api-reference/audio/createTranscription) |
| Websocket streaming API | ✗  No | Jul 20 | [source](https://developers.openai.com/api/docs/api-reference/audio/createTranscription) |

## OpenAI Whisper (API) head-to-head

| Comparison | Record | Per use case |
| --- | --- | --- |
| [OpenAI Whisper (API) vs Deepgram](https://www.versusref.com/stt/deepgram-vs-whisper/) | won 1 · lost 5 · tied 1 | Call Centers: lost; Developers: lost; Dictation: tie; Medical: lost; Meetings: lost; Self-Hosted: won; Voice Agents: lost |
| [OpenAI Whisper (API) vs AssemblyAI](https://www.versusref.com/stt/assemblyai-vs-whisper/) | won 1 · lost 4 · tied 1 | Developers: lost; Dictation: tie; Medical: lost; Meetings: lost; Self-Hosted: won; Voice Agents: lost |
| [OpenAI Whisper (API) vs ElevenLabs Scribe](https://www.versusref.com/stt/elevenlabs-scribe-vs-whisper/) | won 2 · lost 4 · tied 1 | Call Centers: lost; Developers: lost; Dictation: tie; Medical: won; Meetings: lost; Self-Hosted: won; Voice Agents: lost |
| [OpenAI Whisper (API) vs Mistral Voxtral Transcribe](https://www.versusref.com/stt/voxtral-vs-whisper/) | won 1 · lost 5 · tied 1 | Call Centers: lost; Developers: lost; Dictation: tie; Medical: won; Meetings: lost; Self-Hosted: lost; Voice Agents: lost |
| [OpenAI Whisper (API) vs OpenAI gpt-4o-transcribe](https://www.versusref.com/stt/gpt-4o-transcribe-vs-whisper/) | won 0 · lost 3 · tied 3 | Call Centers: lost; Dictation: tie; Medical: tie; Meetings: lost; Self-Hosted: tie; Voice Agents: lost |
| [OpenAI Whisper (API) vs Groq (hosted Whisper)](https://www.versusref.com/stt/groq-whisper-vs-whisper/) | won 1 · lost 4 · tied 2 | Call Centers: lost; Developers: lost; Dictation: tie; Medical: won; Meetings: lost; Self-Hosted: lost; Voice Agents: tie |
| [OpenAI Whisper (API) vs NVIDIA Parakeet / Riva](https://www.versusref.com/stt/nvidia-parakeet-vs-whisper/) | won 2 · lost 4 · tied 1 | Call Centers: lost; Developers: won; Dictation: lost; Medical: won; Meetings: lost; Self-Hosted: lost; Voice Agents: tie |
| [OpenAI Whisper (API) vs Gladia](https://www.versusref.com/stt/gladia-vs-whisper/) | won 2 · lost 3 · tied 2 | Call Centers: tie; Developers: won; Dictation: tie; Medical: lost; Meetings: lost; Self-Hosted: won; Voice Agents: lost |
| [OpenAI Whisper (API) vs Moonshine](https://www.versusref.com/stt/moonshine-vs-whisper/) | won 2 · lost 3 · tied 2 | Call Centers: lost; Developers: won; Dictation: lost; Medical: won; Meetings: tie; Self-Hosted: lost; Voice Agents: tie |
| [OpenAI Whisper (API) vs Qwen3-ASR](https://www.versusref.com/stt/qwen3-asr-vs-whisper/) | won 1 · lost 4 · tied 2 | Call Centers: lost; Developers: lost; Dictation: tie; Medical: won; Meetings: tie; Self-Hosted: lost; Voice Agents: lost |

Source: https://www.versusref.com/stt/tools/whisper/