Class OpenAITranscriptionRequest

Namespace

Glitch9.AIDevKit.OpenAI

Transcribes audio into the input language.

public class OpenAITranscriptionRequest : AIRequest, IMultipartFormRequest

Inheritance

object

AIRequest

OpenAITranscriptionRequest

Implements

IMultipartFormRequest

Inherited Members

AIRequest.Model

AIRequest.N

AIRequest.Metadata

AIRequest.User

AIRequest.SafetyIdentifier

Remarks

returns the transcription object or a verbose transcription object.

Constructors

OpenAITranscriptionRequest()

public OpenAITranscriptionRequest()

OpenAITranscriptionRequest(AudioClip)

public OpenAITranscriptionRequest(AudioClip clip)

Parameters

clip AudioClip

OpenAITranscriptionRequest(File<AudioClip>)

public OpenAITranscriptionRequest(File<AudioClip> file)

Parameters

file File<AudioClip>

Properties

ChunkingStrategy

Optional. Controls how the audio is cut into chunks. When set to "auto", the server first normalizes loudness and then uses voice activity detection (VAD) to choose boundaries. server_vad object can be provided to tweak VAD detection parameters manually. If unset, the audio is transcribed as a single block.

public OpenAITranscriptionRequest.ChunkingStrategyWrapper ChunkingStrategy { get; set; }

Property Value

OpenAITranscriptionRequest.ChunkingStrategyWrapper

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.

public AudioClip File { get; set; }

Property Value

AudioClip

Include

Optional. Additional information to include in the transcription response. logprobs will return the log probabilities of the tokens in the response to understand the model's confidence in the transcription. logprobs only works with response_format set to json and only with the models gpt-4o-transcribe and gpt-4o-mini-transcribe.

public List<string> Include { get; set; }

Property Value

List<string>

Language

The language of the input audio. Supplying the input language in ISO-639-1 format will improve accuracy and latency.

public SystemLanguage? Language { get; set; }

Property Value

SystemLanguage?

Prompt

An optional text to guide the model's style or continue a previous audio segment. The prompt should match the audio language.

public string Prompt { get; set; }

Property Value

string

Stream

Optional. Defaults to false If set to true, the model response data will be streamed to the client as it is generated using server-sent events. See the Streaming section of the Speech-to-Text guide for more information.

Note: Streaming is not supported for the whisper-1 model and will be ignored.

public bool? Stream { get; set; }

Property Value

bool?

Temperature

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.

public float? Temperature { get; set; }

Property Value

float?

TimestampGranularities

The timestamp granularities to populate for this transcription. response_format must be set verbose_json to use timestamp granularities. Either or both of these options are supported: word, or segment.

public string[] TimestampGranularities { get; set; }

Property Value

string[]

Remarks

Note: There is no additional latency for segment timestamps, but generating word timestamps incurs additional latency.