Whisper Large V3 Turbo

Audio input

Hugging Face Website

Speech transcription model for accurate audio-to-text and captioning workflows

Released: 2y ago
Transcription / hour: $0.01

Sources:models.devOpenRouter

Audio pricing is shown only when an audio billing unit is published. Transcription and speech rates are converted to per hour and per 1M characters.

Benchmarks

DeepSWE is the primary coding benchmark where an exact model evaluation exists. Other sourced evaluations appear below; missing scores are not zero.

Not evaluated in DeepSWE 1.1 as of 2026-09-22. Results are only shown for exact model versions in the official dataset. Official leaderboard.

No benchmark results have been matched to this model yet.

Specifications

Developer: OpenAI
Model family: Whisper
Type: Audio model
Predecessor: —
Successor: —
Released: October 1, 2024
Model ID: openai/whisper-large-v3-turbo
Openness: Open weights
License: —
Parameters: —
Input modalities: audio
Output modalities: transcription
Modality: audio->transcription
Hugging Face: openai/whisper-large-v3-turbo
Source freshness: Metadata synced Oct 8, 2026, 10:17 PM UTC

Additional source evidence

Source model: openai/whisper-large-v3-turbo
Source family: whisper
Last updated: 2024-10-01
Model context: 448
Model output limit: 448
Open weights: Yes
File attachments: No
Reasoning: No
Tool calling: No

Complete source record (JSON)

{
  "id": "openai/whisper-large-v3-turbo",
  "name": "Whisper Large v3 Turbo",
  "description": "Speech transcription model for accurate audio-to-text and captioning workflows",
  "family": "whisper",
  "last_updated": "2024-10-01",
  "attachment": false,
  "reasoning": false,
  "tool_call": false,
  "modalities": {
    "input": [
      "audio"
    ],
    "output": [
      "text"
    ]
  },
  "limit": {
    "context": 448,
    "output": 448
  },
  "release_date": "2024-10-01",
  "open_weights": true
}

Infrastructure

Provider availability

All providers

Provider	Endpoint	Pricing (published units)	Uptime 1d	Data handling
DeepInfra	deepinfra/us	$0.01 / hour	100.00%	ZDR: Yes Training: Unknown Prompt logging: Unknown Retention: Unknown ZDR source Privacy policy Checked 2026-10-15
Groq	groq	$0.04 / hour	100.00%	ZDR: Yes Training: Unknown Prompt logging: Unknown Retention: Unknown ZDR source Privacy policy Checked 2026-10-15

Provider data:OpenRouter

Text provenance

EU · product-scoped

OpenAI textGrain watermarking

In the EU, ChatGPT-generated text uses textGrain. OpenAI says API customers can opt in globally for select models, so watermarking depends on the product surface and configuration.

Official explanation

Deployment graph

Can I run this?

Vertical Tabs only shows compatibility when it has structured evidence tying this exact model to hardware, runtime, quantization, memory use, and observed performance.

Browse hardware