Arcade Adventure: Google Cloud ML APIs | GSP119

GSP119 — Speech-to-Text API: Qwik Start

Estimated time: 10 minutes

# 🚀 Google Cloud Speech-to-Text API | GSP119 > ⚠️ **Disclaimer:** This is an independent, community-made walkthrough created for educational purposes, hands-on practice, and Google Cloud certification preparation. This guide is designed to help learners understand the Google Cloud Speech-to-Text API, API key configuration, JSON request payloads, Cloud Storage, and speech recognition workflows through practical exercises. Always attempt the lab yourself first and follow Google Cloud Skills Boos

clear
# Professional ANSI Color Variables
CYAN='\033[1;36m'
GREEN='\033[1;32m'
YELLOW='\033[1;33m'
BLUE='\033[1;34m'
RESET='\033[0m'
BOLD='\033[1m'

echo -e "${CYAN}${BOLD}"
echo "   ____       _    _ _             __   ___             "
echo "  / __ \     | |  (_) |           / _| / _ \            "
echo " | |  | |_ __| |__  _| |_  ___   | |_ | | | |_ __ ___  "
echo " | |  | | '__| '_ \| | __| / _ \ |  _|| | | | '_ \ / __| "
echo " | |__| | |  | |_) | | |_ | (_) || |  | |_| | |_) \__ \ "
echo "  \____/|_|  |_.__/|_|\__| \___/ |_|   \___/| .__/|___/ "
echo "                                            | |         "
echo "                                            |_|         "
echo -e "${RESET}"

export PROJECT_ID=$(gcloud config get-value project)

echo -e "${YELLOW}▶ Task 1: Creating API Key for Cloud Speech-to-Text API...${RESET}"
# Generating the key and applying the strict target restriction required by new lab policies
gcloud services api-keys create --display-name="Speech-Key" \
    --api-target=service=speech.googleapis.com

# Give the API key a few seconds to propagate in the backend
sleep 5

export KEY_NAME=$(gcloud services api-keys list --filter="displayName=Speech-Key" --format="value(name)" | head -n 1)
export API_KEY=$(gcloud services api-keys get-key-string $KEY_NAME --format="value(keyString)")

echo -e "${BLUE}▶ Task 2: Building request.json payload...${RESET}"
cat > request.json <<EOF
{
  "config": {
      "encoding":"FLAC",
      "languageCode": "en-US"
  },
  "audio": {
      "uri":"gs://cloud-samples-tests/speech/brooklyn.flac"
  }
}
EOF

echo -e "${YELLOW}▶ Task 3: Querying the Speech-to-Text API...${RESET}"
curl -s -X POST -H "Content-Type: application/json" --data-binary @request.json \
"https://speech.googleapis.com/v1/speech:recognize?key=${API_KEY}" > result.json

echo -e "${CYAN}▶ Displaying transcription results:${RESET}"
cat result.json

echo -e "\n${BLUE}▶ Uploading results to Cloud Storage...${RESET}"
# Creating the required bucket before attempting the upload
gcloud storage buckets create gs://$PROJECT_ID-speech/ --location=us
gcloud storage cp result.json gs://$PROJECT_ID-speech/

echo -e "${GREEN}✓ All tasks completed! You may now click 'Check my progress' on the lab page.${RESET}"