Package org.springframework.ai.openai

Class OpenAiAudioTranscriptionOptions

java.lang.Object

org.springframework.ai.openai.AbstractOpenAiOptions

org.springframework.ai.openai.OpenAiAudioTranscriptionOptions

All Implemented Interfaces:

AudioTranscriptionOptions, ModelOptions

public class OpenAiAudioTranscriptionOptions
extends AbstractOpenAiOptions
implements AudioTranscriptionOptions

OpenAI SDK Audio Transcription Options.

Author:

Michael Lavelle, Christian Tzolov, Piotr Olaszewski, Ilayaperumal Gopinathan

Nested Class Summary

Nested Classes

Modifier and Type	Class	Description
static final class	OpenAiAudioTranscriptionOptions.Builder

Nested classes/interfaces inherited from class org.springframework.ai.openai.AbstractOpenAiOptions

AbstractOpenAiOptions.AbstractBuilder<O extends AbstractOpenAiOptions,B extends AbstractOpenAiOptions.AbstractBuilder<O,B>>

Field Summary

Fields

Modifier and Type	Field	Description
static final com.openai.models.audio.AudioResponseFormat	DEFAULT_RESPONSE_FORMAT	Default response format.
static final String	DEFAULT_TRANSCRIPTION_MODEL	Default transcription model (Whisper 1).

Fields inherited from class org.springframework.ai.openai.AbstractOpenAiOptions

DEFAULT_MAX_RETRIES, DEFAULT_TIMEOUT

Constructor Summary

Constructors

Modifier	Constructor	Description
protected	OpenAiAudioTranscriptionOptions(@Nullable String baseUrl, @Nullable String apiKey, @Nullable com.openai.credential.Credential credential, @Nullable String model, @Nullable String microsoftDeploymentName, @Nullable com.openai.azure.AzureOpenAIServiceVersion microsoftFoundryServiceVersion, @Nullable String organizationId, @Nullable Boolean isMicrosoftFoundry, @Nullable Boolean isGitHubModels, @Nullable Duration timeout, @Nullable Integer maxRetries, @Nullable Proxy proxy, @Nullable Map<String,String> customHeaders, @Nullable com.openai.models.audio.AudioResponseFormat responseFormat, @Nullable String prompt, @Nullable String language, @Nullable Float temperature, @Nullable List<com.openai.models.audio.transcriptions.TranscriptionCreateParams.TimestampGranularity> timestampGranularities, @Nullable Boolean diarizedJsonWorkaroundEnabled, @Nullable com.openai.models.audio.transcriptions.TranscriptionCreateParams.ChunkingStrategy chunkingStrategy, @Nullable List<String> knownSpeakerNames, @Nullable List<String> knownSpeakerReferences)

Method Summary

Modifier and Type	Method	Description
static OpenAiAudioTranscriptionOptions.Builder	builder()
boolean	equals(@Nullable Object o)
@Nullable com.openai.models.audio.transcriptions.TranscriptionCreateParams.ChunkingStrategy	getChunkingStrategy()	Controls how the audio is cut into chunks when streaming or when the model benefits from voice-activity-detection-based chunking.
@Nullable List<String>	getKnownSpeakerNames()	Speaker identifiers (up to 4) matching, positionally, the audio samples in getKnownSpeakerReferences().
@Nullable List<String>	getKnownSpeakerReferences()	Audio samples (as data URLs, e.g.
@Nullable String	getLanguage()
String	getModel()
@Nullable String	getPrompt()
com.openai.models.audio.AudioResponseFormat	getResponseFormat()
@Nullable Float	getTemperature()
@Nullable List<com.openai.models.audio.transcriptions.TranscriptionCreateParams.TimestampGranularity>	getTimestampGranularities()
int	hashCode()
boolean	isDiarizedJsonWorkaroundEnabled()	Whether the diarized_json misclassification workaround is applied.

Methods inherited from class org.springframework.ai.openai.AbstractOpenAiOptions

getApiKey, getBaseUrl, getCredential, getCustomHeaders, getDeploymentName, getMaxRetries, getMicrosoftDeploymentName, getMicrosoftFoundryServiceVersion, getOrganizationId, getProxy, getTimeout, isGitHubModels, isMicrosoftFoundry

Methods inherited from class java.lang.Object

clone, finalize, getClass, notify, notifyAll, toString, wait, wait, wait

Field Details

DEFAULT_TRANSCRIPTION_MODEL

public static final String DEFAULT_TRANSCRIPTION_MODEL

Default transcription model (Whisper 1).

DEFAULT_RESPONSE_FORMAT

public static final com.openai.models.audio.AudioResponseFormat DEFAULT_RESPONSE_FORMAT

Default response format.

Constructor Details

OpenAiAudioTranscriptionOptions

protected OpenAiAudioTranscriptionOptions(@Nullable String baseUrl,
 @Nullable String apiKey,
 @Nullable com.openai.credential.Credential credential,
 @Nullable String model,
 @Nullable String microsoftDeploymentName,
 @Nullable com.openai.azure.AzureOpenAIServiceVersion microsoftFoundryServiceVersion,
 @Nullable String organizationId,
 @Nullable Boolean isMicrosoftFoundry,
 @Nullable Boolean isGitHubModels,
 @Nullable Duration timeout,
 @Nullable Integer maxRetries,
 @Nullable Proxy proxy,
 @Nullable Map<String,String> customHeaders,
 @Nullable com.openai.models.audio.AudioResponseFormat responseFormat,
 @Nullable String prompt,
 @Nullable String language,
 @Nullable Float temperature,
 @Nullable List<com.openai.models.audio.transcriptions.TranscriptionCreateParams.TimestampGranularity> timestampGranularities,
 @Nullable Boolean diarizedJsonWorkaroundEnabled,
 @Nullable com.openai.models.audio.transcriptions.TranscriptionCreateParams.ChunkingStrategy chunkingStrategy,
 @Nullable List<String> knownSpeakerNames,
 @Nullable List<String> knownSpeakerReferences)

Method Details

builder

public static OpenAiAudioTranscriptionOptions.Builder builder()

getModel

public String getModel()

Specified by:

getModel in interface AudioTranscriptionOptions

Overrides:

getModel in class AbstractOpenAiOptions

getResponseFormat

public com.openai.models.audio.AudioResponseFormat getResponseFormat()

getPrompt

public @Nullable String getPrompt()

getLanguage

public @Nullable String getLanguage()

getTemperature

public @Nullable Float getTemperature()

getTimestampGranularities

public @Nullable List<com.openai.models.audio.transcriptions.TranscriptionCreateParams.TimestampGranularity> getTimestampGranularities()

isDiarizedJsonWorkaroundEnabled

public boolean isDiarizedJsonWorkaroundEnabled()

Whether the diarized_json misclassification workaround is applied. See DiarizedJsonMisclassificationRecovery for background. Defaults to true.

getChunkingStrategy

public @Nullable com.openai.models.audio.transcriptions.TranscriptionCreateParams.ChunkingStrategy getChunkingStrategy()

Controls how the audio is cut into chunks when streaming or when the model benefits from voice-activity-detection-based chunking. Build one via TranscriptionCreateParams.ChunkingStrategy.ofAuto() or TranscriptionCreateParams.ChunkingStrategy.ofVadConfig(com.openai.models.audio.transcriptions.TranscriptionCreateParams.ChunkingStrategy.VadConfig).

getKnownSpeakerNames

public @Nullable List<String> getKnownSpeakerNames()

Speaker identifiers (up to 4) matching, positionally, the audio samples in getKnownSpeakerReferences(). Only used with the gpt-4o-transcribe-diarize model.

getKnownSpeakerReferences

public @Nullable List<String> getKnownSpeakerReferences()

Audio samples (as data URLs, e.g. data:audio/wav;base64,...) containing known speaker references, positionally matching getKnownSpeakerNames(). Only used with the gpt-4o-transcribe-diarize model.

equals

public boolean equals(@Nullable Object o)

Overrides:

equals in class Object

hashCode

public int hashCode()

Overrides:

hashCode in class Object