Implementation:Groq Groq python Translations Create

Knowledge Sources	Groq Python SDK Groq API Docs
Domains	Audio, Translation
Last Updated	2026-02-15 16:00 GMT

Overview

Concrete tool for translating audio into English provided by the Groq Python SDK's audio translation resource.

Description

The Translations class (and its async counterpart AsyncTranslations) provides the create() method to translate audio content into English using Groq-hosted Whisper models. It sends a multipart POST request to the /openai/v1/audio/translations endpoint. The method accepts audio as a file upload or URL, and supports configuring the model variant, output format, sampling temperature, and an optional English-language prompt for style guidance.

Usage

Import and use this when you need to translate non-English audio into English text. Access it via client.audio.translations.create(). For transcription (same language) use client.audio.transcriptions.create() instead.

Code Reference

Source Location

• Repository: Groq Python SDK
• File: src/groq/resources/audio/translations.py
• Lines: 1-254

Signature

class Translations(SyncAPIResource):
    def create(
        self,
        *,
        model: Union[str, Literal["whisper-large-v3", "whisper-large-v3-turbo"]],
        file: FileTypes | Omit = omit,
        prompt: str | Omit = omit,
        response_format: Literal["json", "text", "verbose_json"] | Omit = omit,
        temperature: float | Omit = omit,
        url: str | Omit = omit,
        extra_headers: Headers | None = None,
        extra_query: Query | None = None,
        extra_body: Body | None = None,
        timeout: float | httpx.Timeout | None | NotGiven = not_given,
    ) -> Translation:
        """Translates audio into English."""

Import

from groq import Groq

client = Groq()
# Access via: client.audio.translations.create(...)

I/O Contract

Inputs

Name	Type	Required	Description
model	str or Literal["whisper-large-v3", "whisper-large-v3-turbo"]	Yes	Whisper model ID to use for translation
file	FileTypes	No*	Audio file (flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, webm). *Either file or url required.
url	str	No*	Audio URL (supports Base64URL). *Either file or url required.
prompt	str	No	English text to guide model style or continue a previous segment
response_format	Literal["json", "text", "verbose_json"]	No	Output format for the translation
temperature	float	No	Sampling temperature (0-1); 0 uses log-probability auto-increase
extra_headers	Headers or None	No	Additional HTTP headers
timeout	float or Timeout or None	No	Per-request timeout override

Outputs

Name	Type	Description
return	Translation	Translation result containing the translated English text

Usage Examples

Translate an Audio File

from groq import Groq

client = Groq()

# Translate a French audio file to English
with open("french_audio.mp3", "rb") as audio_file:
    translation = client.audio.translations.create(
        model="whisper-large-v3-turbo",
        file=audio_file,
        response_format="json",
    )

print(translation.text)

Translate from URL

from groq import Groq

client = Groq()

translation = client.audio.translations.create(
    model="whisper-large-v3",
    url="https://example.com/spanish_audio.mp3",
    prompt="This is a conversation about technology.",
    temperature=0.2,
)

print(translation.text)

Async Translation

import asyncio
from groq import AsyncGroq

async def translate_audio():
    client = AsyncGroq()

    with open("german_audio.wav", "rb") as f:
        translation = await client.audio.translations.create(
            model="whisper-large-v3-turbo",
            file=f,
        )

    return translation.text

result = asyncio.run(translate_audio())

Related Pages

• Environment:Groq_Groq_python_Python_Groq_SDK