Class TranscriptionRequest

Transcribes audio into the input language.

Inheritance
object
RESTRequestBody
OpenAIRequest
TranscriptionRequest
Inherited Members
Namespace: Glitch9.AIDevKit.OpenAI
Assembly: .dll
Syntax
public class TranscriptionRequest : OpenAIRequest
Remarks

returns the transcription object or a verbose transcription object.

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.

Declaration
public TranscriptionRequest.ChunkingStrategyWrapper ChunkingStrategy { get; set; }
Property Value
Type Description
TranscriptionRequest.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.

Declaration
public File<AudioClip> File { get; set; }
Property Value
Type Description
File<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.

Declaration
public List<string> Include { get; set; }
Property Value
Type Description
List<string>

Language

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

Declaration
public SystemLanguage? Language { get; set; }
Property Value
Type Description
SystemLanguage?

Prompt

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

Declaration
public string Prompt { get; set; }
Property Value
Type Description
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.

Declaration
public bool? Stream { get; set; }
Property Value
Type Description
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.

Declaration
public float? Temperature { get; set; }
Property Value
Type Description
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.

Declaration
public string[] TimestampGranularities { get; set; }
Property Value
Type Description
string[]
Remarks

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

Extension Methods