Audio Translations

Looking for transcriptions? See Audio Transcriptions, or learn about the difference between translations and transcriptions below.

Currently, audio can only be translated into English.

Audio translation converts spoken language from an audio recording into written text in another language. Common uses include:

Converting user-uploaded audio in diverse languages into text in a single language.
Translating interviews, lectures, and meetings for journalists, students, researchers, and professionals.
Powering voice assistants that understand and respond to commands in different languages.
Providing instant translations of spoken exercises in language-learning applications.
Automatically generating subtitles for movies, shows, and online videos.

Audio translations are served by OpenAI models through the endpoint below.

Request

URL: https://ai.purlabs.xyz/openai/audio/translations

Request Method: POST


interface Request {
  file: string;
  model: string;
  prompt?: string;
  response_format?: string;
  temperature?: number;
}

Property	Type	Required	Description
`file`	`File`	Required	The audio file object (not file name) to transcribe, in one of these formats: `flac`, `mp3`, `mp4`, `mpeg`, `mpga`, `m4a`, `ogg`, `wav`, or `webm`.
`model`	`string`	Required	ID of the model to use. Only `whisper-1` is currently available.
`prompt`	`string`	Optional	An optional text to guide the model’s style or continue a previous audio segment. The prompt should match the audio language.
`response_format`	`string`	Optional	Defaults to `json`. The format of the transcript output, in one of these options: json, text, srt, verbose_json, or vtt.
`temperature`	`number`	Optional	Defaults to `0`. The sampling temperature, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. If set to 0, the model will use log probability to automatically increase the temperature until certain thresholds are hit.


{
  "file": "https://my-audio-sample.com/audio.mp3",
  "model": "whisper-1",
}


interface Response {
  text: string;
};


{
  "text": "Good morning everyone, and welcome to today's presentation on renewable energy."
}

Aspect	Audio Transcriptions	Translations
Definition	Conversion of spoken language from audio to text.	Conversion of written text from one language to another while maintaining its meaning.
Purpose	Provides a written record of spoken content.	Enables understanding of content across different languages and cultures.
Output Format	Textual representation of spoken words.	Textual representation of content in another language.
Accessibility	Enhances access for people with hearing impairments.	Bridges communication gaps for non-native speakers.
Indexing	Improves search engine visibility through text.	Expands content’s reach to global audiences.
Use Cases	Podcasts, interviews, meetings, content repurposing.	Localization, global communication, reaching diverse audiences.
Process	Typing out spoken words heard in an audio recording.	Converting written content from one language to another, considering cultural nuances.
Skill Required	Accurate listening and transcription abilities.	Bilingual proficiency, cultural understanding, and language skills.
Tools	Manual transcription or automated speech recognition software.	Human translators or machine translation tools.
Output Utility	Provides a readable version of audio content.	Enables comprehension and engagement with content regardless of language barriers.