Package org.springframework.ai.openai

Class OpenAiAudioTranscriptionOptions.Builder

java.lang.Object

org.springframework.ai.openai.AbstractOpenAiOptions.AbstractBuilder<OpenAiAudioTranscriptionOptions,OpenAiAudioTranscriptionOptions.Builder>

org.springframework.ai.openai.OpenAiAudioTranscriptionOptions.Builder

Enclosing class:

OpenAiAudioTranscriptionOptions

public static final class OpenAiAudioTranscriptionOptions.Builder
extends AbstractOpenAiOptions.AbstractBuilder<OpenAiAudioTranscriptionOptions,OpenAiAudioTranscriptionOptions.Builder>

Field Summary

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

apiKey, baseUrl, credential, customHeaders, isGitHubModels, isMicrosoftFoundry, maxRetries, microsoftDeploymentName, microsoftFoundryServiceVersion, model, organizationId, proxy, timeout

Method Summary

Modifier and Type	Method	Description
OpenAiAudioTranscriptionOptions	build()
OpenAiAudioTranscriptionOptions.Builder	chunkingStrategy(@Nullable com.openai.models.audio.transcriptions.TranscriptionCreateParams.ChunkingStrategy chunkingStrategy)	Controls how the audio is cut into chunks.
OpenAiAudioTranscriptionOptions.Builder	diarizedJsonWorkaroundEnabled(boolean diarizedJsonWorkaroundEnabled)	Enables or disables the diarized_json misclassification workaround.
OpenAiAudioTranscriptionOptions.Builder	from(OpenAiAudioTranscriptionOptions fromOptions)
OpenAiAudioTranscriptionOptions.Builder	knownSpeakerNames(@Nullable List<String> knownSpeakerNames)	Speaker identifiers (up to 4), positionally matching knownSpeakerReferences.
OpenAiAudioTranscriptionOptions.Builder	knownSpeakerReferences(@Nullable List<String> knownSpeakerReferences)	Audio samples (as data URLs) containing known speaker references, positionally matching knownSpeakerNames.
OpenAiAudioTranscriptionOptions.Builder	language(@Nullable String language)
OpenAiAudioTranscriptionOptions.Builder	merge(@Nullable org.springframework.ai.audio.transcription.AudioTranscriptionOptions from)
OpenAiAudioTranscriptionOptions.Builder	prompt(@Nullable String prompt)
OpenAiAudioTranscriptionOptions.Builder	responseFormat(@Nullable com.openai.models.audio.AudioResponseFormat responseFormat)
OpenAiAudioTranscriptionOptions.Builder	temperature(@Nullable Float temperature)
OpenAiAudioTranscriptionOptions.Builder	timestampGranularities(@Nullable List<com.openai.models.audio.transcriptions.TranscriptionCreateParams.TimestampGranularity> timestampGranularities)

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

apiKey, apiKey, azure, azureOpenAIServiceVersion, baseUrl, credential, customHeaders, deploymentName, gitHubModels, maxRetries, microsoftFoundry, microsoftFoundryServiceVersion, model, organizationId, proxy, self, timeout

Methods inherited from class java.lang.Object

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

Method Details

from

public OpenAiAudioTranscriptionOptions.Builder from(OpenAiAudioTranscriptionOptions fromOptions)

merge

public OpenAiAudioTranscriptionOptions.Builder merge(@Nullable org.springframework.ai.audio.transcription.AudioTranscriptionOptions from)

responseFormat

public OpenAiAudioTranscriptionOptions.Builder responseFormat(@Nullable com.openai.models.audio.AudioResponseFormat responseFormat)

prompt

public OpenAiAudioTranscriptionOptions.Builder prompt(@Nullable String prompt)

language

public OpenAiAudioTranscriptionOptions.Builder language(@Nullable String language)

temperature

public OpenAiAudioTranscriptionOptions.Builder temperature(@Nullable Float temperature)

timestampGranularities

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

diarizedJsonWorkaroundEnabled

public OpenAiAudioTranscriptionOptions.Builder diarizedJsonWorkaroundEnabled(boolean diarizedJsonWorkaroundEnabled)

Enables or disables the diarized_json misclassification workaround. Enabled by default. See DiarizedJsonMisclassificationRecovery for background.

chunkingStrategy

public OpenAiAudioTranscriptionOptions.Builder chunkingStrategy(@Nullable com.openai.models.audio.transcriptions.TranscriptionCreateParams.ChunkingStrategy chunkingStrategy)

Controls how the audio is cut into chunks. Use TranscriptionCreateParams.ChunkingStrategy.ofAuto() for the default server-side auto-chunking, or TranscriptionCreateParams.ChunkingStrategy.ofVadConfig(com.openai.models.audio.transcriptions.TranscriptionCreateParams.ChunkingStrategy.VadConfig) to tune voice-activity-detection parameters.

knownSpeakerNames

public OpenAiAudioTranscriptionOptions.Builder knownSpeakerNames(@Nullable List<String> knownSpeakerNames)

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

knownSpeakerReferences

public OpenAiAudioTranscriptionOptions.Builder knownSpeakerReferences(@Nullable List<String> knownSpeakerReferences)

Audio samples (as data URLs) containing known speaker references, positionally matching knownSpeakerNames. Only used with the gpt-4o-transcribe-diarize model.

build

public OpenAiAudioTranscriptionOptions build()

Specified by:

build in class AbstractOpenAiOptions.AbstractBuilder<OpenAiAudioTranscriptionOptions,OpenAiAudioTranscriptionOptions.Builder>