deepgram-go-audio-intelligence

Utiliser lors de l'écriture ou de la révision de code Go dans ce dépôt qui applique des résumés, des sujets, des intentions, des sentiments, la détection de langue, la diarisation, la rédaction ou des entités…

Using Deepgram Audio Intelligence from the Go SDK

When to use this product

Use this skill for /v1/listen REST requests that combine transcription with analytics overlays.

summaries
topics
intents
sentiments
entity extraction
language detection
diarization and redaction where supported

Use a different skill when:

you only need transcription (deepgram-go-speech-to-text)
your input is already text (deepgram-go-text-intelligence)

Authentication

Set DEEPGRAM_API_KEY before creating the listen REST client.

export DEEPGRAM_API_KEY="your_api_key"

Quick start

package main

import (
	"context"
	"fmt"
	"log"

	api "github.com/deepgram/deepgram-go-sdk/v3/pkg/api/listen/v1/rest"
	listen "github.com/deepgram/deepgram-go-sdk/v3/pkg/client/listen"
	interfaces "github.com/deepgram/deepgram-go-sdk/v3/pkg/client/interfaces"
)

func main() {
	if err := run(); err != nil {
		log.Fatal(err)
	}
}

func run() error {
	ctx := context.Background()

	client := listen.NewRESTWithDefaults()
	dg := api.New(client)

	resp, err := dg.FromURL(
		ctx,
		"https://dpgr.am/spacewalk.wav",
		&interfaces.PreRecordedTranscriptionOptions{
			Model:     "nova-3",
			Summarize: "v2",
			Topics:    true,
			Sentiment: true,
		},
	)
	if err != nil {
		return err
	}

	if resp.Results.Summary != nil {
		fmt.Println(resp.Results.Summary.Result)
	}
	return nil
}

Key parameters

analytics live on interfaces.PreRecordedTranscriptionOptions
- Summarize (for example, "v2")
- Topics
- Intents
- Sentiment
- DetectLanguage
- DetectEntities
- Diarize
- DiarizeModel
- Redact
response payloads are in pkg/api/listen/v1/rest/interfaces/types.go
- Sentiments
- Topics
- Intents
- Entities
- SummaryV2
this SDK is REST-first for audio intelligence; the live WS option struct does not expose the same analytics surface

API reference (layered)

In-repo reference
- README.md
- docs.go
- pkg/client/listen/v1/rest/client.go
- pkg/client/interfaces/v1/types-prerecorded.go
- pkg/client/interfaces/v1/types-stream.go
- pkg/api/listen/v1/rest/interfaces/types.go
OpenAPI
- https://developers.deepgram.com/openapi.yaml
AsyncAPI
- https://developers.deepgram.com/asyncapi.yaml
Context7
- /llmstxt/developers_deepgram_llms_txt
Product docs
- https://developers.deepgram.com/docs/stt-intelligence-feature-overview
- https://developers.deepgram.com/docs/summarization
- https://developers.deepgram.com/docs/topic-detection
- https://developers.deepgram.com/docs/intent-recognition
- https://developers.deepgram.com/docs/sentiment-analysis
- https://developers.deepgram.com/docs/language-detection
- https://developers.deepgram.com/docs/redaction
- https://developers.deepgram.com/docs/diarization

Gotchas

In this SDK snapshot, audio intelligence is effectively a prerecorded REST feature set.
LiveTranscriptionOptions does not expose the same summarize/topic/intent/sentiment/entity surface.
REST helpers live on pkg/api/listen/v1/rest; start from api.New(listen.NewRESTWithDefaults()), then layer analytics flags onto PreRecordedTranscriptionOptions.

Example files in this repo

examples/speech-to-text/rest/summary/main.go
examples/speech-to-text/rest/sentiment/main.go
examples/speech-to-text/rest/topic/main.go
examples/speech-to-text/rest/intent/main.go

Central product skills

For cross-language Deepgram product knowledge — the consolidated API reference, documentation finder, focused runnable recipes, third-party integration examples, and MCP setup — install the central skills:

npx skills add deepgram/skills

This SDK ships language-idiomatic code skills; deepgram/skills ships cross-language product knowledge (see api, docs, recipes, examples, starters, setup-mcp).