Whisper Medium vs Distil Whisper Large V3
Compare the listed model data for Whisper Medium by openai and Distil Whisper Large V3 by distil-whisper. 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
LITHOVEX lists Whisper Medium at 30-second audio chunks and Distil Whisper Large V3 at a large context window. Check provider documentation for current specifications. Whisper Medium is listed for no specific capability flags; Distil Whisper Large V3 is listed for no specific capability flags. Shared catalog benchmark entries: WER (LibriSpeech clean): Whisper Medium 3.0%; Distil Whisper Large V3 2.8%; WER (LibriSpeech other): Whisper Medium 5.6%; Distil Whisper Large V3 5.5%. 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.
Computed differences from catalog data
- A context-window ratio cannot be calculated from the catalog values (30-second audio chunks for Whisper Medium; a large context window for Distil Whisper Large V3).
- On shared numeric benchmark entries, WER (LibriSpeech clean): Whisper Medium − Distil Whisper Large V3 = +0.2 percentage points (3.0% vs 2.8%); WER (LibriSpeech other): Whisper Medium − Distil Whisper Large V3 = +0.1 percentage points (5.6% vs 5.5%).
- The first listed parameter quantities are 307M and 756M; the larger quantity is 2.46× the smaller. Total and active MoE parameters are not directly equivalent.
- The catalog release dates are September 2022 and November 2023, 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 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.
Choose Distil Whisper Large V3 if…
Choose Distil Whisper Large V3 when your task aligns with catalog-listed uses or strengths such as High-throughput English transcription, Applications where Large v3 latency is unacceptable, 6x faster than Large v3 with <1% WER degradation on English, MIT license — free.
Whisper Medium
OpenAI's Whisper Medium — balanced multilingual transcription model. Faster than Large with only a small accuracy trade-off.
Parameters: 307M
Context: 30-second audio chunks
Catalog pricing: MIT — free
Distil Whisper Large V3
Distil-Whisper — 6× faster than Whisper Large V3 and 49% smaller, with within-1% transcription accuracy. English-focused.
Parameters: 756M
Catalog pricing: MIT — free
Feature Comparison — Whisper Medium vs Distil Whisper Large V3
| Specification | Whisper Medium | Distil Whisper Large V3 |
|---|---|---|
| Provider | openai | distil-whisper |
| Parameters | 307M | 756M |
| Context window | 30-second audio chunks | Not listed |
| Maximum output | Not listed | Not listed |
| Catalog pricing | MIT — free | 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) | 3.0% | 2.8% |
| Benchmark: WER (LibriSpeech other) | 5.6% | 5.5% |
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 Medium and Distil Whisper Large V3?
What benchmark values are listed for Whisper Medium and Distil Whisper Large V3?
Which model has the larger listed context window?
What are the listed costs per million tokens for Whisper Medium and Distil Whisper Large V3?
How far apart are the listed release dates for Whisper Medium and Distil Whisper Large V3?
When was the comparison data last updated?
How should I choose between Whisper Medium and Distil Whisper Large V3?
Explore these models and related comparisons
Read the Whisper Medium model profile and Distil Whisper Large V3 model profile, or browse the model directory.