Compare the listed model data for Whisper Large V3 by openai and Whisper Medium by openai. Benchmark and pricing records are not a controlled test and may change.
Data last updated: 2026-10-16. Verify current model details with each provider.
What the listed data says
Whisper Large V3: 30-second audio chunks; Whisper Medium: 30-second audio chunks. The listed context-window values are equal. Whisper Large V3 is listed for no specific capability flags; Whisper Medium is listed for no specific capability flags. Shared catalog benchmark entries: WER (LibriSpeech clean): Whisper Large V3 2.7%; Whisper Medium 3.0%; WER (LibriSpeech other): Whisper Large V3 5.2%; Whisper Medium 5.6%. These records are reference data, not a controlled head-to-head test; verify current pricing and specifications with each provider.
Catalog source links
Use these model and provider links to verify current specifications, pricing, and availability.
The listed context windows are 30-second audio chunks and 30-second audio chunks; the larger is 1× the smaller.
On shared numeric benchmark entries, WER (LibriSpeech clean): Whisper Large V3 − Whisper Medium = -0.3 percentage points (2.7% vs 3.0%); WER (LibriSpeech other): Whisper Large V3 − Whisper Medium = -0.4 percentage points (5.2% vs 5.6%).
The first listed parameter quantities are 1.55B and 307M; the larger quantity is 5.05× the smaller. Total and active MoE parameters are not directly equivalent.
The catalog release dates are November 2023 and September 2022, about 14 months apart at the precision supplied.
Cost example: 1M input and 1M output tokens
A cost example for 1M input plus 1M output tokens cannot be calculated reliably because separate numeric input and output rates are not listed for both models.
Choose Whisper Large V3 if…
Choose Whisper Large V3 when your task aligns with catalog-listed uses or strengths such as Meeting transcription and subtitle generation, Podcast and video content indexing, Medical consultation transcription, Research on multilingual speech across 99 languages.
Choose Whisper Medium if…
Choose Whisper Medium when your task aligns with catalog-listed uses or strengths such as Fast batch transcription where Large v3 latency is unacceptable, English-primary transcription at lower cost, Balance of accuracy and speed — faster than Large v3 for English, MIT license.
Feature Comparison — Whisper Large V3 vs Whisper Medium
Catalog specifications for Whisper Large V3 and Whisper Medium
Specification
Whisper Large V3
Whisper Medium
Provider
openai
openai
Parameters
1.55B
307M
Context window
30-second audio chunks
30-second audio chunks
Maximum output
Not listed
Not listed
Catalog pricing
MIT — free. OpenAI API: $0.006/minute transcription
MIT — free
Listed input/output cost per 1M tokens
Separate numeric input/output rates not listed
Separate numeric input/output rates not listed
License
MIT
MIT
Coding support
Not listed
Not listed
Reasoning support
Not listed
Not listed
Vision input
Not listed
Not listed
Multimodal
Not listed
Not listed
Open weights
Yes
Yes
Benchmark: WER (LibriSpeech clean)
2.7%
3.0%
Benchmark: WER (LibriSpeech other)
5.2%
5.6%
Figures are transcribed from LITHOVEX model records. Benchmark versions and evaluation setups may differ; pricing and specifications can change. Check each provider's current documentation before making a decision.
Frequently Asked Questions
What is different between Whisper Large V3 and Whisper Medium?
Whisper Large V3: 30-second audio chunks; Whisper Medium: 30-second audio chunks. The listed context-window values are equal. Whisper Large V3 is listed for no specific capability flags; Whisper Medium is listed for no specific capability flags. Shared catalog benchmark entries: WER (LibriSpeech clean): Whisper Large V3 2.7%; Whisper Medium 3.0%; WER (LibriSpeech other): Whisper Large V3 5.2%; Whisper Medium 5.6%. These records are reference data, not a controlled head-to-head test; verify current pricing and specifications with each provider.
What benchmark values are listed for Whisper Large V3 and Whisper Medium?
WER (LibriSpeech clean): Whisper Large V3 2.7%; Whisper Medium 3.0%; WER (LibriSpeech other): Whisper Large V3 5.2%; Whisper Medium 5.6%. The catalog values may use different versions and evaluation setups, so they are reference points rather than a controlled head-to-head result.
Which model has the larger listed context window?
Whisper Large V3: 30-second audio chunks; Whisper Medium: 30-second audio chunks. The listed context-window values are equal.
What are the listed costs per million tokens for Whisper Large V3 and Whisper Medium?
Whisper Large V3: Separate numeric input/output rates not listed (MIT — free. OpenAI API: $0.006/minute transcription). Whisper Medium: Separate numeric input/output rates not listed (MIT — free). Where separate numeric input and output rates are available, the worked example uses 1M input plus 1M output tokens. Confirm current terms with each provider.
How far apart are the listed release dates for Whisper Large V3 and Whisper Medium?
The catalog lists Whisper Large V3 as November 2023 and Whisper Medium as September 2022, about 14 months apart at the precision supplied.
When was the comparison data last updated?
The model catalog records 2026-10-16 as its data update date. Provider specifications and prices may have changed since then.
How should I choose between Whisper Large V3 and Whisper Medium?
Compare the listed specifications and capabilities, review the benchmark notes, then test both with the same representative prompt for your task. This page does not claim a universal winner.
Create your free LITHOVEX account and compare Whisper Large V3 and Whisper Medium on your actual tasks. No credit card, no API key, no subscriptions needed.