Audio understanding

AUDIO_PATH="path/to/sample.mp3"
MIME_TYPE=$(file -b --mime-type "${AUDIO_PATH}")
NUM_BYTES=$(wc -c < "${AUDIO_PATH}")
DISPLAY_NAME=AUDIO

tmp_header_file=upload-header.tmp

# Initial resumable request defining metadata.
# The upload url is in the response headers dump them to a file.
curl "https://generativelanguage.googleapis.com/upload/v1beta/files?key=${GOOGLE_API_KEY}" \
  -D upload-header.tmp \
  -H "X-Goog-Upload-Protocol: resumable" \
  -H "X-Goog-Upload-Command: start" \
  -H "X-Goog-Upload-Header-Content-Length: ${NUM_BYTES}" \
  -H "X-Goog-Upload-Header-Content-Type: ${MIME_TYPE}" \
  -H "Content-Type: application/json" \
  -d "{'file': {'display_name': '${DISPLAY_NAME}'}}" 2> /dev/null

upload_url=$(grep -i "x-goog-upload-url: " "${tmp_header_file}" | cut -d" " -f2 | tr -d "\r")
rm "${tmp_header_file}"

# Upload the actual bytes.
curl "${upload_url}" \
  -H "Content-Length: ${NUM_BYTES}" \
  -H "X-Goog-Upload-Offset: 0" \
  -H "X-Goog-Upload-Command: upload, finalize" \
  --data-binary "@${AUDIO_PATH}" 2> /dev/null > file_info.json

file_uri=$(jq ".file.uri" file_info.json)
echo file_uri=$file_uri

# Now generate content using that file
curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-2.0-flash:generateContent?key=$GOOGLE_API_KEY" \
    -H 'Content-Type: application/json' \
    -X POST \
    -d '{
      "contents": [{
        "parts":[
          {"text": "Describe this audio clip"},
          {"file_data":{"mime_type": "${MIME_TYPE}", "file_uri": '$file_uri'}}]
        }]
      }' 2> /dev/null > response.json

cat response.json
echo

jq ".candidates[].content.parts[].text" response.json

from google.genai import types

with open('path/to/small-sample.mp3', 'rb') as f:
    audio_bytes = f.read()

response = client.models.generate_content(
  model='gemini-2.0-flash',
  contents=[
    'Describe this audio clip',
    types.Part.from_bytes(
      data=audio_bytes,
      mime_type='audio/mp3',
    )
  ]
)

print(response.text)

myfile = client.files.upload(file='path/to/sample.mp3')
prompt = 'Generate a transcript of the speech.'

response = client.models.generate_content(
  model='gemini-2.0-flash',
  contents=[prompt, myfile]
)

print(response.text)

# Create a prompt containing timestamps.
prompt = "Provide a transcript of the speech from 02:30 to 03:29."

response = client.models.count_tokens(
  model='gemini-2.0-flash',
  contents=[myfile]
)

print(response)