Skip to main content
View as MarkdownOpen in ChatGPTOpen in Claude

LMNT Provider

LMNT provides text-to-speech synthesis with voice selection and speed control. The current Go provider implements the shared provider.SpeechModel interface and is used through ai.GenerateSpeech.

Setup​

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

    "github.com/digitallysavvy/go-ai/pkg/ai"
    "github.com/digitallysavvy/go-ai/pkg/providers/lmnt"
)
provider := lmnt.New(lmnt.Config{
    APIKey: os.Getenv("LMNT_API_KEY"),
})

model, err := provider.SpeechModel("default")
if err != nil {
    log.Fatal(err)
}

Generate Speech​

speed := 1.2
result, err := ai.GenerateSpeech(context.Background(), ai.GenerateSpeechOptions{
    Model: model,
    Text:  "Welcome to the Go AI SDK.",
    Voice: "aurora",
    Speed: &speed,
})
if err != nil {
    log.Fatal(err)
}

if err := os.WriteFile("output.mp3", result.Audio.Data, 0644); err != nil {
    log.Fatal(err)
}

fmt.Printf("Generated %d bytes as %s\n", len(result.Audio.Data), result.Audio.MediaType)

Voices​

Common voices include aurora, lily, harper, and sage. Voice defaults to "ava" when left empty. Check the LMNT documentation for the complete voice list.

See Also​