Table of Contents

Class AudioTranscriptionRequest

Namespace
OpenAI.Audio
Assembly
OpenAI-DotNet.dll
public sealed class AudioTranscriptionRequest : IDisposable
Inheritance
AudioTranscriptionRequest
Implements
Inherited Members

Constructors

AudioTranscriptionRequest(Stream, string, string, ChunkingStrategy, string[], string, string, AudioResponseFormat, float?, TimestampGranularity)

Constructor.

public AudioTranscriptionRequest(Stream audio, string audioName, string model = null, ChunkingStrategy chunkingStrategy = null, string[] include = null, string language = null, string prompt = null, AudioResponseFormat responseFormat = AudioResponseFormat.Json, float? temperature = null, TimestampGranularity timestampGranularity = TimestampGranularity.None)

Parameters

audio Stream

The audio stream to transcribe.

audioName string

The name of the audio file to transcribe.

model string

ID of the model to use. Only whisper-1 is currently available.

chunkingStrategy ChunkingStrategy

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.

include string[]

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.

language string

Optional, The language of the input audio. Supplying the input language in ISO-639-1 format will improve accuracy and latency.
Currently supported languages: Afrikaans, Arabic, Armenian, Azerbaijani, Belarusian, Bosnian, Bulgarian, Catalan, Chinese, Croatian, Czech, Danish, Dutch, English, Estonian, Finnish, French, Galician, German, Greek, Hebrew, Hindi, Hungarian, Icelandic, Indonesian, Italian, Japanese, Kannada, Kazakh, Korean, Latvian, Lithuanian, Macedonian, Malay, Marathi, Maori, Nepali, Norwegian, Persian, Polish, Portuguese, Romanian, Russian, Serbian, Slovak, Slovenian, Spanish, Swahili, Swedish, Tagalog, Tamil, Thai, Turkish, Ukrainian, Urdu, Vietnamese, and Welsh.

prompt string

Optional, An optional text to guide the model's style or continue a previous audio segment.
The prompt should be in English.

responseFormat AudioResponseFormat

Optional, The format of the transcript output, in one of these options: json, text, srt, verbose_json, or vtt.
Defaults to json.

temperature float?

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.
Defaults to 0

timestampGranularity TimestampGranularity

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

AudioTranscriptionRequest(Stream, string, string, string, AudioResponseFormat, float?, string, TimestampGranularity) 

[Obsolete("Use new .ctr overload with chunkingStrategy and include")]
public AudioTranscriptionRequest(Stream audio, string audioName, string model, string prompt, AudioResponseFormat responseFormat, float? temperature, string language, TimestampGranularity timestampGranularity)

Parameters

audio Stream
audioName string
model string
prompt string
responseFormat AudioResponseFormat
temperature float?
language string
timestampGranularity TimestampGranularity

AudioTranscriptionRequest(string, string, ChunkingStrategy, string[], string, string, AudioResponseFormat, float?, TimestampGranularity)

Constructor.

public AudioTranscriptionRequest(string audioPath, string model = null, ChunkingStrategy chunkingStrategy = null, string[] include = null, string language = null, string prompt = null, AudioResponseFormat responseFormat = AudioResponseFormat.Json, float? temperature = null, TimestampGranularity timestampGranularity = TimestampGranularity.None)

Parameters

audioPath string

The audio file to transcribe, in one of these formats flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, or webm.

model string

ID of the model to use.

chunkingStrategy ChunkingStrategy

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.

include string[]

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.

language string

Optional, The language of the input audio. Supplying the input language in ISO-639-1 format will improve accuracy and latency.
Currently supported languages: Afrikaans, Arabic, Armenian, Azerbaijani, Belarusian, Bosnian, Bulgarian, Catalan, Chinese, Croatian, Czech, Danish, Dutch, English, Estonian, Finnish, French, Galician, German, Greek, Hebrew, Hindi, Hungarian, Icelandic, Indonesian, Italian, Japanese, Kannada, Kazakh, Korean, Latvian, Lithuanian, Macedonian, Malay, Marathi, Maori, Nepali, Norwegian, Persian, Polish, Portuguese, Romanian, Russian, Serbian, Slovak, Slovenian, Spanish, Swahili, Swedish, Tagalog, Tamil, Thai, Turkish, Ukrainian, Urdu, Vietnamese, and Welsh.

prompt string

Optional, An optional text to guide the model's style or continue a previous audio segment.
The prompt should be in English.

responseFormat AudioResponseFormat

Optional, The format of the transcript output, in one of these options: json, text, srt, verbose_json, or vtt.
Defaults to json.

temperature float?

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.
Defaults to 0

timestampGranularity TimestampGranularity

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

AudioTranscriptionRequest(string, string, string, AudioResponseFormat, float?, string, TimestampGranularity) 

[Obsolete("Use new .ctr overload with chunkingStrategy and include")]
public AudioTranscriptionRequest(string audioPath, string model, string prompt, AudioResponseFormat responseFormat, float? temperature, string language, TimestampGranularity timestampGranularity)

Parameters

audioPath string
model string
prompt string
responseFormat AudioResponseFormat
temperature float?
language string
timestampGranularity TimestampGranularity

Properties

Audio

The audio file to transcribe, in one of these formats: flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, or webm.

public Stream Audio { get; }

Property Value

Stream

AudioName

The name of the audio file to transcribe.

public string AudioName { get; }

Property Value

string

ChunkingStrategy

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 ChunkingStrategy ChunkingStrategy { get; }

Property Value

ChunkingStrategy

Include

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 string[] Include { get; }

Property Value

string[]

Language

Optional, The language of the input audio. Supplying the input language in ISO-639-1 format will improve accuracy and latency.
Currently supported languages: Afrikaans, Arabic, Armenian, Azerbaijani, Belarusian, Bosnian, Bulgarian, Catalan, Chinese, Croatian, Czech, Danish, Dutch, English, Estonian, Finnish, French, Galician, German, Greek, Hebrew, Hindi, Hungarian, Icelandic, Indonesian, Italian, Japanese, Kannada, Kazakh, Korean, Latvian, Lithuanian, Macedonian, Malay, Marathi, Maori, Nepali, Norwegian, Persian, Polish, Portuguese, Romanian, Russian, Serbian, Slovak, Slovenian, Spanish, Swahili, Swedish, Tagalog, Tamil, Thai, Turkish, Ukrainian, Urdu, Vietnamese, and Welsh.

public string Language { get; }

Property Value

string

Model

ID of the model to use. Only whisper-1 is currently available.

public string Model { get; }

Property Value

string

Prompt

Optional, An optional text to guide the model's style or continue a previous audio segment.
The prompt should be in English.

public string Prompt { get; }

Property Value

string

ResponseFormat

Optional, The format of the transcript output, in one of these options: json, text, srt, verbose_json, or vtt.
Defaults to json.

public AudioResponseFormat ResponseFormat { get; }

Property Value

AudioResponseFormat

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.
Defaults to 0

public float? Temperature { get; }

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

public TimestampGranularity TimestampGranularities { get; }

Property Value

TimestampGranularity

Methods

Dispose()

Performs application-defined tasks associated with freeing, releasing, or resetting unmanaged resources.

public void Dispose()

~AudioTranscriptionRequest() 

protected ~AudioTranscriptionRequest()
Edit this page