Whisper Large v3 Turbo

OpenAI

openai/whisper-large-v3-turboOpen Weights

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

Benchmark Pricing$0.00 / 1M in$0.00 / 1M out

Context: 448 tokens•Max Output: 448 tokens•Released: 2024-10-01

TECHNICAL SPECIFICATIONS

Context Window448448 tokens

Max Output448448 tokens

LicenseOpen SourceSelf-hostable

Input Modalities

TextAudio

Function / Tool CallingNot Supported

Structured OutputsPrompt Based

MODEL CONTEXT PROTOCOL (MCP) READINESS

⚠ Whisper Large v3 Turbo does not natively advertise tool-calling capabilities. When connecting to MCP servers, function calling must be handled via structured prompt injection.

MCP Context Window Recommendations

With a context capacity of 448 tokens, this model can handle compact tool sets. Consider keeping MCP server tool manifests minimal to preserve headroom.

API CALL INVOCATION EXAMPLE

// Example: Calling Whisper Large v3 Turbo via OpenAI SDK
import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.OPENAI_API_KEY,
});

const response = await client.chat.completions.create({
  model: "openai/whisper-large-v3-turbo",
  messages: [{ role: "user", content: "Hello! Can you inspect MCP tools?" }],
});

console.log(response.choices[0].message.content);