SpeechModel Interface

Interface that all speech synthesis (text-to-speech) model implementations must satisfy.

Interface Definition

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

    // Speech synthesis
    DoGenerate(ctx context.Context, opts *SpeechGenerateOptions) (*types.SpeechResult, error)
}

Methods

Method	Parameters	Returns	Description
SpecificationVersion()	-	string	Specification version
Provider()	-	string	Provider name
ModelID()	-	string	Model identifier
DoGenerate()	ctx, *SpeechGenerateOptions	*types.SpeechResult, error	Generate speech audio

SpeechGenerateOptions

type SpeechGenerateOptions struct {
    Text  string
    Voice string
    Speed *float64
}

Examples

Using a Speech Model

package main

import (
    "context"
    "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.SpeechModel("tts-1")
    if err != nil {
        log.Fatal(err)
    }

    result, err := model.DoGenerate(context.Background(), &provider.SpeechGenerateOptions{
        Text:  "Hello, world!",
        Voice: "alloy",
    })
    if err != nil {
        log.Fatal(err)
    }

    os.WriteFile("output.mp3", result.Audio, 0644)
}

See Also

• GenerateSpeech - High-level speech generation
• TranscriptionModel - Speech-to-text interface
• Custom Provider - Implementing custom providers