main.go

package main

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

	"github.com/google/generative-ai-go/genai"
	"google.golang.org/api/option"
)

func main() {
	ctx := context.Background()
	apiKey, ok := os.LookupEnv("GEMINI_API_KEY")
	if !ok {
		log.Fatal("Environment variable GEMINI_API_KEY not set")
	}
	client, err := genai.NewClient(ctx, option.WithAPIKey(apiKey))
	if err != nil {
		log.Fatalf("Error creating client: %v", err)
	}
	defer client.Close()

	model := client.GenerativeModel("gemini-1.5-pro-exp-0801")

	model.SetTemperature(1)
	model.SetTopK(64)
	model.SetTopP(0.95)
	model.SetMaxOutputTokens(8192)
	model.ResponseMIMEType = "text/plain"
	model.SafetySettings = []*genai.SafetySetting{
		{Category: genai.HarmCategoryHarassment, Threshold: genai.HarmBlockNone},
	}

	session := model.StartChat()

	f, err := os.Open("/Users/jbd/Downloads/sample-0.mp3")
	if err != nil {
		log.Fatalf("Failed to open file: %v", err)
	}
	content, err := io.ReadAll(f)
	if err != nil {
		log.Fatalf("Failed to read the contents: %v", err)
	}

	const bufferSize = 8192
	for i := 0; i < len(content); i += bufferSize {
		endx := i + bufferSize
		if endx > len(content) {
			endx = len(content)
		}
		log.Printf("Transcribing from %d to %d", i, endx)
		resp, err := session.SendMessage(ctx, genai.Text("Transcribe the audio."), genai.Blob{
			MIMEType: "audio/mp3",
			Data:     content[i:endx],
		})
		if err != nil {
			log.Fatalf("Error sending message: %v", err)
		}
		for _, part := range resp.Candidates[0].Content.Parts {
			fmt.Printf("%v\n", part)
		}
	}
}

The output:

2024/08/13 16:35:59 Transcribing from 0 to 8192
He does P-

2024/08/13 16:36:00 Transcribing from 8192 to 16384
Doesn't to be long P-

2024/08/13 16:36:01 Transcribing from 16384 to 24576
to you. A P-

2024/08/13 16:36:02 Transcribing from 24576 to 32768
And I don't see P-
...