Package org.springframework.ai.audio.transcription

Interface TranscriptionModel

All Superinterfaces:
Model<AudioTranscriptionPrompt,AudioTranscriptionResponse>
public interface TranscriptionModel extends Model<AudioTranscriptionPrompt,AudioTranscriptionResponse>
A transcription model is a type of AI model that converts audio to text. This is also known as Speech-to-Text.
Since:
1.0.0
Author:
Mudabir Hussain

  • Method Summary

    Modifier and Type
    Method
    Description
    AudioTranscriptionResponse
    call(AudioTranscriptionPrompt transcriptionPrompt)
    Transcribes the audio from the given prompt.
    default String
    transcribe(org.springframework.core.io.Resource resource)
    A convenience method for transcribing an audio resource.
    default String
    transcribe(org.springframework.core.io.Resource resource, AudioTranscriptionOptions options)
    A convenience method for transcribing an audio resource with the given options.

  • Method Details

    • call

      AudioTranscriptionResponse call(AudioTranscriptionPrompt transcriptionPrompt)
      Transcribes the audio from the given prompt.
      Specified by:
      call in interface Model<AudioTranscriptionPrompt,AudioTranscriptionResponse>
      Parameters:
      transcriptionPrompt - The prompt containing the audio resource and options.
      Returns:
      The transcription response.

    • transcribe

      default String transcribe(org.springframework.core.io.Resource resource)
      A convenience method for transcribing an audio resource.
      Parameters:
      resource - The audio resource to transcribe.
      Returns:
      The transcribed text.

    • transcribe

      default String transcribe(org.springframework.core.io.Resource resource, AudioTranscriptionOptions options)
      A convenience method for transcribing an audio resource with the given options.
      Parameters:
      resource - The audio resource to transcribe.
      options - The transcription options.
      Returns:
      The transcribed text.