Skip to main content
View as MarkdownOpen in ChatGPTOpen in Claude

Gladia Provider

Gladia provides speech-to-text transcription. The current Go provider implements the shared provider.TranscriptionModel interface and is used through ai.Transcribe.

Setup​

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

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

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

Gladia has a single transcription model, not a selectable catalog — the model ID argument is kept for interface parity with other providers but is not sent in the request; pass an empty string.

Transcribe Audio​

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

result, err := ai.Transcribe(context.Background(), ai.TranscribeOptions{
    Model:    model,
    Audio:    audioData,
    MimeType: "audio/mpeg",
    ProviderOptions: map[string]interface{}{
        "gladia": map[string]interface{}{
            "language": "en",
        },
    },
})
if err != nil {
    log.Fatal(err)
}

fmt.Println(result.Text)
if result.DurationInSeconds != nil {
    fmt.Printf("Duration: %.2f seconds\n", *result.DurationInSeconds)
}

Timestamps​

result, err := ai.Transcribe(context.Background(), ai.TranscribeOptions{
    Model:    model,
    Audio:    audioData,
    MimeType: "audio/mpeg",
    ProviderOptions: map[string]interface{}{
        "gladia": map[string]interface{}{
            "detectLanguage": true,
        },
    },
})
if err != nil {
    log.Fatal(err)
}

for _, segment := range result.Segments {
    fmt.Printf("[%.2f-%.2f] %s\n", segment.StartSecond, segment.EndSecond, segment.Text)
}

Workflow Serialization​

Gladia transcription models can cross a workflow boundary with provider.SerializeTranscriptionModel / DeserializeTranscriptionModel. See Provider Serialization for the mechanism.

See Also​