การถอดเสียงเป็นคำ

from google import genai

client = genai.Client()

audio_file = client.files.upload(file="path/to/sample.mp3")

response = client.models.generate_content(
    model="gemini-3.5-transcribe",
    contents=[audio_file],
)

print(response.text)

import { GoogleGenAI } from "@google/genai";

const ai = new GoogleGenAI({});

const audioFile = await ai.files.upload({
  file: "path/to/sample.mp3",
  mimeType: "audio/mp3",
});

const response = await ai.models.generateContent({
  model: "gemini-3.5-transcribe",
  contents: [audioFile],
});

console.log(response.text);

# First upload the file via the Files API, then pass its URI:
curl -X POST "https://generativelanguage.googleapis.com/v1beta/models/gemini-3.5-transcribe:generateContent" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "contents": [
      {
        "parts": [
          {
            "fileData": {
              "fileUri": "YOUR_FILE_URI",
              "mimeType": "audio/mp3"
            }
          }
        ]
      }
    ]
  }'

from google import genai
from google.genai import types

client = genai.Client()

response = client.models.generate_content(
    model="gemini-3.5-transcribe",
    contents=[audio_file],
    config=types.GenerateContentConfig(
        audio_transcription_config=types.AudioTranscriptionConfig(
            language_codes=[],
        )
    ),
)

const response = await ai.models.generateContent({
  model: "gemini-3.5-transcribe",
  contents: [audioFile],
  config: {
    audioTranscriptionConfig: {
      languageCodes: [],
    },
  },
});

curl -X POST "https://generativelanguage.googleapis.com/v1beta/models/gemini-3.5-transcribe:generateContent" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "contents": [
      {
        "parts": [
          {
            "fileData": {
              "fileUri": "YOUR_FILE_URI",
              "mimeType": "audio/mp3"
            }
          }
        ]
      }
    ],
    "generationConfig": {
      "audioTranscriptionConfig": {
        "languageCodes": []
      }
    }
  }'

config = types.GenerateContentConfig(
    audio_transcription_config=types.AudioTranscriptionConfig(
        language_codes=["es-ES"],
    )
)

const config = {
  audioTranscriptionConfig: {
    languageCodes: ["es-ES"],
  },
};

{
  "generationConfig": {
    "audioTranscriptionConfig": {
      "languageCodes": ["es-ES"]
    }
  }
}

from google import genai
from google.genai import types

client = genai.Client()

response = client.models.generate_content(
    model="gemini-3.5-transcribe",
    contents=[audio_file],
    config=types.GenerateContentConfig(
        audio_transcription_config=types.AudioTranscriptionConfig(
            custom_vocabulary=["Gemini", "Kubernetes", "BigQuery"],
        )
    ),
)

const response = await ai.models.generateContent({
  model: "gemini-3.5-transcribe",
  contents: [audioFile],
  config: {
    audioTranscriptionConfig: {
      customVocabulary: ["Gemini", "Kubernetes", "BigQuery"],
    },
  },
});

curl -X POST "https://generativelanguage.googleapis.com/v1beta/models/gemini-3.5-transcribe:generateContent" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "contents": [
      {
        "parts": [
          {
            "fileData": {
              "fileUri": "YOUR_FILE_URI",
              "mimeType": "audio/mp3"
            }
          }
        ]
      }
    ],
    "generationConfig": {
      "audioTranscriptionConfig": {
        "customVocabulary": ["Gemini", "Kubernetes", "BigQuery"]
      }
    }
  }'

from google import genai
from google.genai import types

client = genai.Client()

response = client.models.generate_content(
    model="gemini-3.5-transcribe",
    contents=[audio_file],
    config=types.GenerateContentConfig(
        audio_transcription_config=types.AudioTranscriptionConfig(
            diarization=True,
        )
    ),
)

const response = await ai.models.generateContent({
  model: "gemini-3.5-transcribe",
  contents: [audioFile],
  config: {
    audioTranscriptionConfig: {
      diarization: true,
    },
  },
});

curl -X POST "https://generativelanguage.googleapis.com/v1beta/models/gemini-3.5-transcribe:generateContent" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "contents": [
      {
        "parts": [
          {
            "fileData": {
              "fileUri": "YOUR_FILE_URI",
              "mimeType": "audio/mp3"
            }
          }
        ]
      }
    ],
    "generationConfig": {
      "audioTranscriptionConfig": {
        "diarization": true
      }
    }
  }'

from google import genai
from google.genai import types

client = genai.Client()

response = client.models.generate_content(
    model="gemini-3.5-transcribe",
    contents=[audio_file],
    config=types.GenerateContentConfig(
        audio_transcription_config=types.AudioTranscriptionConfig(
            word_timestamp=True,
        )
    ),
)

const response = await ai.models.generateContent({
  model: "gemini-3.5-transcribe",
  contents: [audioFile],
  config: {
    audioTranscriptionConfig: {
      wordTimestamp: true,
    },
  },
});

curl -X POST "https://generativelanguage.googleapis.com/v1beta/models/gemini-3.5-transcribe:generateContent" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "contents": [
      {
        "parts": [
          {
            "fileData": {
              "fileUri": "YOUR_FILE_URI",
              "mimeType": "audio/mp3"
            }
          }
        ]
      }
    ],
    "generationConfig": {
      "audioTranscriptionConfig": {
        "wordTimestamp": true
      }
    }
  }'

config = types.GenerateContentConfig(
    audio_transcription_config=types.AudioTranscriptionConfig(
        diarization=True,
        word_timestamp=True,
        custom_vocabulary=["Gemini"],
    )
)

const config = {
  audioTranscriptionConfig: {
    diarization: true,
    wordTimestamp: true,
    customVocabulary: ["Gemini"],
  },
};

{
  "generationConfig": {
    "audioTranscriptionConfig": {
      "diarization": true,
      "wordTimestamp": true,
      "customVocabulary": ["Gemini"]
    }
  }
}

from google import genai
from google.genai import types

client = genai.Client()

response = client.models.generate_content(
    model="gemini-3.5-transcribe",
    contents=[audio_file],
    config=types.GenerateContentConfig(
        audio_transcription_config=types.AudioTranscriptionConfig(
            mode="SMART",
        )
    ),
)
print(response.text)

const response = await ai.models.generateContent({
  model: "gemini-3.5-transcribe",
  contents: [audioFile],
  config: {
    audioTranscriptionConfig: {
      mode: "SMART",
    },
  },
});
console.log(response.text);

curl -X POST "https://generativelanguage.googleapis.com/v1beta/models/gemini-3.5-transcribe:generateContent" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "contents": [
      {
        "parts": [
          {
            "fileData": {
              "fileUri": "YOUR_FILE_URI",
              "mimeType": "audio/mp3"
            }
          }
        ]
      }
    ],
    "generationConfig": {
      "audioTranscriptionConfig": {
        "mode": "SMART"
      }
    }
  }'

def extract_word_transcriptions(response):
    words = []
    for candidate in getattr(response, "candidates", []) or []:
        content = getattr(candidate, "content", None)
        for part in getattr(content, "parts", []) or []:
            transcription = getattr(part, "audio_transcription", None)
            if transcription:
                speaker = getattr(transcription, "speaker_label", "")
                for word_info in getattr(transcription, "words", []) or []:
                    word = getattr(word_info, "word", "")
                    start = getattr(word_info, "start_offset", "")
                    end = getattr(word_info, "end_offset", "")
                    words.append({
                        "word": word,
                        "speaker": speaker,
                        "start_offset": start,
                        "end_offset": end,
                    })
    return words

words = extract_word_transcriptions(response)

for w in words:
    speaker = f"[{w['speaker']}] " if w["speaker"] else ""
    timing = f"({w['start_offset']} -> {w['end_offset']}) " if w["start_offset"] and w["end_offset"] else ""
    print(f"{speaker}{timing}{w['word']}")

function extractWordTranscriptions(response) {
  const words = [];
  for (const candidate of response.candidates ?? []) {
    for (const part of candidate.content?.parts ?? []) {
      const transcription = part.audioTranscription;
      if (transcription) {
        const speaker = transcription.speakerLabel ?? "";
        for (const wordInfo of transcription.words ?? []) {
          words.push({
            word: wordInfo.word ?? "",
            speaker: speaker,
            startOffset: wordInfo.startOffset ?? "",
            endOffset: wordInfo.endOffset ?? "",
          });
        }
      }
    }
  }
  return words;
}

const words = extractWordTranscriptions(response);

for (const w of words) {
  const speaker = w.speaker ? `[${w.speaker}] ` : "";
  const timing = (w.startOffset && w.endOffset) ? `(${w.startOffset} -> ${w.endOffset}) ` : "";
  console.log(`${speaker}${timing}${w.word}`);
}

{
  "candidates": [
    {
      "content": {
        "parts": [
          {
            "audioTranscription": {
              "speakerLabel": "spk_1",
              "words": [
                {
                  "word": "Hello",
                  "startOffset": "0.100s",
                  "endOffset": "0.450s"
                },
                {
                  "word": "world",
                  "startOffset": "0.500s",
                  "endOffset": "0.850s"
                }
              ]
            }
          }
        ],
        "role": "model"
      },
      "finishReason": "STOP"
    }
  ]
}