TranscriptionModel Interface

Interface that all speech-to-text transcription model implementations must satisfy.

Interface Definition

type TranscriptionModel interface {
    // Metadata
    SpecificationVersion() string
    Provider() string
    ModelID() string

    // Transcription
    DoTranscribe(ctx context.Context, opts *TranscriptionOptions) (*types.TranscriptionResult, error)
}

Methods

Method	Parameters	Returns	Description
SpecificationVersion()	-	string	Specification version
Provider()	-	string	Provider name
ModelID()	-	string	Model identifier
DoTranscribe()	ctx, *TranscriptionOptions	*types.TranscriptionResult, error	Transcribe audio to text

TranscriptionOptions

type TranscriptionOptions struct {
    Audio      []byte
    MimeType   string
    Language   string
    Timestamps bool
}

Examples

Using a Transcription Model

package main

import (
    "context"
    "fmt"
    "log"
    "os"

    "github.com/digitallysavvy/go-ai/pkg/provider"
    "github.com/digitallysavvy/go-ai/pkg/providers/openai"
)

func main() {
    p := openai.New(openai.Config{
        APIKey: "your-api-key",
    })
    model, err := p.TranscriptionModel("whisper-1")
    if err != nil {
        log.Fatal(err)
    }

    audioData, err := os.ReadFile("audio.mp3")
    if err != nil {
        log.Fatal(err)
    }

    result, err := model.DoTranscribe(context.Background(), &provider.TranscriptionOptions{
        Audio:    audioData,
        MimeType: "audio/mpeg",
        Language: "en",
    })
    if err != nil {
        log.Fatal(err)
    }

    fmt.Println("Transcription:", result.Text)
}

See Also

• Transcribe - High-level transcription function
• SpeechModel - Text-to-speech interface
• Custom Provider - Implementing custom providers