Implementation:Togethercomputer Together python Translations Create

Knowledge Sources	Together Python
Domains	Audio, Translation
Last Updated	2026-02-15 16:00 GMT

Overview

Concrete tool for translating audio content into English text provided by the Together Python SDK.

Description

The Translations class provides audio translation functionality, converting audio in any supported language to English text. It accepts the same file input types as Transcriptions (local paths, URLs, file objects) and supports response format, temperature, and timestamp granularity options.

Usage

Import this class when you need to translate non-English audio to English text. Access via client.audio.translations.create().

Code Reference

Source Location

Repository: Together Python
File: src/together/resources/audio/translations.py
Lines: 1-276

Signature

class Translations:
    def create(
        self,
        *,
        file: Union[str, BinaryIO, Path],
        model: str = "openai/whisper-large-v3",
        language: Optional[str] = None,
        prompt: Optional[str] = None,
        response_format: Union[str, AudioTranscriptionResponseFormat] = "json",
        temperature: float = 0.0,
        timestamp_granularities: Optional[Union[str, AudioTimestampGranularities]] = None,
    ) -> Union[AudioTranslationResponse, AudioTranslationVerboseResponse]: ...

Import

from together import Together

client = Together()
# Access via client.audio.translations

I/O Contract

Inputs

Name	Type	Required	Description
file	Union[str, BinaryIO, Path]	Yes	Audio file path, URL, or file object
model	str	No	Model ID (default: "openai/whisper-large-v3")
language	str	No	Source audio language (ISO-639-1)
response_format	str	No	"json" or "verbose_json"
temperature	float	No	Sampling temperature 0-1 (default: 0.0)

Outputs

Name	Type	Description
returns (json)	AudioTranslationResponse	Translated English text
returns (verbose_json)	AudioTranslationVerboseResponse	Translated text with timestamps and segments

Usage Examples

from together import Together

client = Together()

# Translate French audio to English
result = client.audio.translations.create(
    file="french_speech.mp3",
    model="openai/whisper-large-v3",
    language="fr",
)
print(result.text)  # English translation

# Verbose with timestamps
result = client.audio.translations.create(
    file="german_meeting.wav",
    response_format="verbose_json",
)
print(result.text)
for seg in result.segments:
    print(f"[{seg.start:.1f}-{seg.end:.1f}] {seg.text}")

Related Pages

Page Connections

Double-click a node to navigate. Hold to expand connections.

Principle

Implementation

Heuristic

Environment