openai
OpenAI: Whisper Large V3
openai/whisper-large-v3
Our take
AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.
openai/whisper-large-v3 is OpenAI's open-source multilingual speech recognition model, listed on OpenRouter for audio-to-transcription workloads with support for 99+ languages and common audio formats. Per its Hugging Face documentation, it is a 1.55B-parameter encoder-decoder trained on five million hours of labeled and pseudo-labeled audio, offering transcription, speech translation into English, and optional timestamps. The model card reports 10-20% fewer errors than large-v2, though this pack contains no independent measurements.[1][2]
Strengths
- Transcribes audio in 99+ languages and translates speech into English, with automatic language detection and optional sentence- or word-level timestamps.[1][2]
- Released under Apache-2.0 and integrated with Hugging Face Transformers, including batching, chunked long-form transcription, and fine-tuning guidance.[2]
- Vendor documentation reports a 10-20% error reduction over whisper-large-v2 across many languages; this is a source-reported claim, not an independently measured result.[2]
Limitations
- Evidence is catalog- and vendor-documentation-only; the pack includes no independent benchmarks, so accuracy and latency should be validated on your own audio workloads.[1][2]
- Speech translation targets English only, and this checkpoint exists solely as a multilingual model with no English-only variant.[2]
- Documentation cautions against use without speaker consent or in high-risk decision contexts, and states that classification-style tasks are unevaluated and inappropriate.[2]
Where to use it
- Suggested: multilingual transcription pipelines, either self-hosted via Transformers or through a hosted endpoint, after validation on representative audio.[1][2]
- Suggested: translating foreign-language speech into English text for research, drafting, or prototyping workflows.[2]
- Suggested: generating timestamped transcripts for media or meeting archives, with human review where accuracy is critical.[2]
Sources
- [1] OpenRouter catalog · OpenAI: Whisper Large V3Sources checked: Nov 13, 2026
- [2] Model documentation · OpenAI: Whisper Large V3Sources checked: Nov 13, 2026
About this model
Description below is the original text supplied by OpenRouter, shown in the source language.
Whisper Large V3 is OpenAI's open-source automatic speech recognition model offering both audio transcription and translation. It supports 99+ languages and accepts common audio formats including mp3, mp4, wav, webm,...
Specifications
- Model ID
- openai/whisper-large-v3
- Creator
- openai
- Added to OpenRouter
- 01.05.2026
- Context length
- 0
- Modality
- audio->transcription
- Input modalities
- audio
- Output modalities
- transcription
- Token pricing
- No per-token price in the source snapshot — see OpenRouter for the billing unit
- Knowledge cutoff
- —
- Expiration date
- —
Tasks and capabilities
A grade appears only where the source supplies a matching measurement for that task, the model is active and the cohort holds at least 10 comparable models. The capability column lists facts the source declares — supported formats, reasoning and tool parameters — which are not measured quality.
| Task | Grade | Source-declared capability |
|---|---|---|
| General quality | No measurement | — |
| Coding | No measurement | — |
| Agents | No measurement | — |
| Writing | No measurement | — |
| Reasoning | No measurement | — |
| Document analysis | No measurement | — |
| Vision | No measurement | — |
| Image generation | No measurement | — |
| Audio | No measurement | input: audio |
| Video | No measurement | — |
| Embeddings | No measurement | — |
Evaluations
No evaluations are supplied for this model.
How grades work
Each letter grade compares a model only against other models scored by the same source and metric in the current snapshot. S means the top 10%, A the next 20%, B the next 30%, C the rest. Models without a published measurement are shown as not rated — a supported format alone never implies measured quality.
- S — S — top 10% of the cohort
- A — A — next 20% of the cohort
- B — B — next 30% of the cohort
- C — C — below the B band
Providers
Optional live provider statistics from OpenRouter. Missing values are unknown, not zero.
| Provider | Context length | Price in /1M | Price out /1M | Latency p50 (30m, s) | Throughput p50 (30m, tok/s) | Uptime (30m) |
|---|---|---|---|---|---|---|
| DeepInfra | 0 | — | — | — | — | 100% |
| Together | 0 | — | — | — | — | 100% |
| Groq | 0 | — | — | — | — | 100% |
Provider data retrieved: 13.11.2026
Related articles
No published articles identify this model yet.