Transcription · OpenAI (Wizper: fal)

Whisper

OpenAI's open speech model: the widest language coverage here at the same low price as Parakeet, in private mode.

Private Low cost
Latest versionWhisper large v3November 2023
Artificial Analysis word error rate4.1%#3 of 4 on Artificial Analysis word error rate
Price$0.162 per hour of audioWhisper Large V3
Key spec99 languages

What sets it apart

Whisper is OpenAI's open speech model, trained on 5 million hours of audio and covering 99 languages, the widest range here. Large v3 cut errors by 10% to 20% compared with large v2, and Wizper serves the same weights faster.

  • 99 languages, Apache 2.0
  • 1.55B parameters, large v3
  • Wizper: same weights, served faster

Recommended for: transcribe several languages or strong accents.

Strengths and limits

Where it shines

  • Best multilingual accuracy in Sub Rosa's suggestions
  • Close to 100 languages
  • Same low price as Parakeet, private mode

Think twice when

  • Can invent text over long silences or noise
  • Whisper Large V3, open weights

Use cases

Transcribe an interview in a less common language

Transcribe this interview recorded in Polish, then give me an English translation below it.

It covers 99 languages, more than any other option here.

Get a transcript back quickly

Transcribe this 20-minute podcast episode as plain text, no timestamps.

Wizper returns the same transcript faster, per fal.

Against its rivals

  • ParakeetParakeet is smaller and punctuates by default, for 25 languages only.
  • ScribeScribe adds speaker labels and sound tags, is more accurate on the Artificial Analysis test, and costs more.#1 of 4 on Artificial Analysis word error rate (2.2%)
  • xAI Speech to TextxAI is cheaper and more accurate on that test, with 25+ languages.#2 of 4 on Artificial Analysis word error rate (4%)
Compare side by side ↗

Version history

Each version, dated, with what it changed over the one before.

  1. Whisper large v2Earlier, not in Sub Rosa
    • Open multilingual speech model with 1.55B parameters
    Source : huggingface.co
  2. Whisper large v3
    • 128 mel frequency bins instead of 80
    • New Cantonese language token and 10% to 20% fewer errors than large v2
    Source : huggingface.co
  3. Wizper (Whisper v3, fal edition)Latest
    • Whisper v3 large with optimized serving: same word error rate, twice the speed, per fal
    Source : fal.ai

Benchmarks

How to read these scores: what a benchmark tells you.

Artificial Analysis word error rate: #3 of 4 models measured in the catalog. The share of words a transcription gets wrong (missed, added or replaced) on a mixed set of real recordings. Lower is better. At 5%, one word in twenty needs fixing; under 3% a transcript reads almost clean.

Artificial Analysis word error rateLower is better · Artificial Analysis, October 4, 2026
  1. 1. ElevenLabs Scribe V2Scribe2.2%
  2. 2. xAI Speech to Text v1xAI Speech to Text4%
  3. 3. Whisper Large V3Whisper4.1%
  4. 4. Wizper (Whisper v3)Whisper4.7%
See the numbers
Model%
1. ElevenLabs Scribe V22.2%
2. xAI Speech to Text v14%
3. Whisper Large V34.1%
4. Wizper (Whisper v3)4.7%

All 2 models in this family

ModelUsePrivacyPrice
Whisper Large V3openai/whisper-large-v3TranscriptionPrivate$0.162 per hour of audio
Wizper (Whisper v3)fal-ai/wizperTranscriptionPrivate$0.162 per hour of audio

Specifications

SpecificationWhisper large v3
ReleasedNovember 2023
Parameters1.55B
WeightsOpen, Apache 2.0
Acceptsaudio
Producestext
Languages99 languages
Price$0.162 per hour of audio
PrivacyPrivate

Prices, context and lengths from the live catalog on October 16, 2026; parameters and licenses from the maker.