অডিও ট্রান্সক্রিপশন

from google import genai

client = genai.Client()

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

interaction = client.interactions.create(
    model="gemini-3.5-transcribe",
    input=[
        {
            "type": "audio",
            "uri": audio_file.uri,
            "mime_type": audio_file.mime_type,
        }
    ],
)

print(interaction.output_text)

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

const client = new GoogleGenAI({});

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

const interaction = await client.interactions.create({
  model: "gemini-3.5-transcribe",
  input: [
    {
      type: "audio",
      uri: audioFile.uri,
      mime_type: audioFile.mimeType,
    },
  ],
});

console.log(interaction.output_text);

# First upload the file via the Files API, then pass its URI:
curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-3.5-transcribe",
    "input": [
      {
        "type": "audio",
        "uri": "YOUR_FILE_URI",
        "mime_type": "audio/mp3"
      }
    ]
  }'

interaction = client.interactions.create(
    model="gemini-3.5-transcribe",
    input=[
        {
            "type": "audio",
            "uri": audio_file.uri,
            "mime_type": audio_file.mime_type,
        }
    ],
    generation_config={
        "transcription_config": {
            "language_codes": [],
        }
    },
)

const interaction = await client.interactions.create({
  model: "gemini-3.5-transcribe",
  input: [
    {
      type: "audio",
      uri: audioFile.uri,
      mime_type: audioFile.mimeType,
    },
  ],
  generation_config: {
    transcription_config: {
      language_codes: [],
    },
  },
});

curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-3.5-transcribe",
    "input": [
      {
        "type": "audio",
        "uri": "YOUR_FILE_URI",
        "mime_type": "audio/mp3"
      }
    ],
    "generation_config": {
      "transcription_config": {
        "language_codes": []
      }
    }
  }'

generation_config = {
    "transcription_config": {
        "language_codes": ["es-ES"],
    }
}

const generationConfig = {
  transcription_config: {
    language_codes: ["es-ES"],
  },
};

{
  "generation_config": {
    "transcription_config": {
      "language_codes": ["es-ES"]
    }
  }
}

interaction = client.interactions.create(
    model="gemini-3.5-transcribe",
    input=[
        {
            "type": "audio",
            "uri": audio_file.uri,
            "mime_type": audio_file.mime_type,
        }
    ],
    generation_config={
        "transcription_config": {
            "custom_vocabulary": ["Gemini", "Kubernetes", "BigQuery"],
        }
    },
)

const interaction = await client.interactions.create({
  model: "gemini-3.5-transcribe",
  input: [
    {
      type: "audio",
      uri: audioFile.uri,
      mime_type: audioFile.mimeType,
    },
  ],
  generation_config: {
    transcription_config: {
      custom_vocabulary: ["Gemini", "Kubernetes", "BigQuery"],
    },
  },
});

curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-3.5-transcribe",
    "input": [
      {
        "type": "audio",
        "uri": "YOUR_FILE_URI",
        "mime_type": "audio/mp3"
      }
    ],
    "generation_config": {
      "transcription_config": {
        "custom_vocabulary": ["Gemini", "Kubernetes", "BigQuery"]
      }
    }
  }'

interaction = client.interactions.create(
    model="gemini-3.5-transcribe",
    input=[
        {
            "type": "audio",
            "uri": audio_file.uri,
            "mime_type": audio_file.mime_type,
        }
    ],
    generation_config={
        "transcription_config": {
            "mode": {
                "type": "verbatim",
                "diarization_mode": "speaker",
            },
        }
    },
)

const interaction = await client.interactions.create({
  model: "gemini-3.5-transcribe",
  input: [
    {
      type: "audio",
      uri: audioFile.uri,
      mime_type: audioFile.mimeType,
    },
  ],
  generation_config: {
    transcription_config: {
      mode: {
        type: "verbatim",
        diarization_mode: "speaker",
      },
    },
  },
});

curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-3.5-transcribe",
    "input": [
      {
        "type": "audio",
        "uri": "YOUR_FILE_URI",
        "mime_type": "audio/mp3"
      }
    ],
    "generation_config": {
      "transcription_config": {
        "mode": {
          "type": "verbatim",
          "diarization_mode": "speaker"
        }
      }
    }
  }'

interaction = client.interactions.create(
    model="gemini-3.5-transcribe",
    input=[
        {
            "type": "audio",
            "uri": audio_file.uri,
            "mime_type": audio_file.mime_type,
        }
    ],
    generation_config={
        "transcription_config": {
            "mode": {
                "type": "verbatim",
                "timestamp_granularities": ["word"],
            },
        }
    },
)

const interaction = await client.interactions.create({
  model: "gemini-3.5-transcribe",
  input: [
    {
      type: "audio",
      uri: audioFile.uri,
      mime_type: audioFile.mimeType,
    },
  ],
  generation_config: {
    transcription_config: {
      mode: {
        type: "verbatim",
        timestamp_granularities: ["word"],
      },
    },
  },
});

curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-3.5-transcribe",
    "input": [
      {
        "type": "audio",
        "uri": "YOUR_FILE_URI",
        "mime_type": "audio/mp3"
      }
    ],
    "generation_config": {
      "transcription_config": {
        "mode": {
          "type": "verbatim",
          "timestamp_granularities": ["word"]
        }
      }
    }
  }'

generation_config = {
    "transcription_config": {
        "custom_vocabulary": ["Gemini"],
        "mode": {
            "type": "verbatim",
            "diarization_mode": "speaker",
            "timestamp_granularities": ["word"],
        },
    }
}

const generationConfig = {
  transcription_config: {
    custom_vocabulary: ["Gemini"],
    mode: {
      type: "verbatim",
      diarization_mode: "speaker",
      timestamp_granularities: ["word"],
    },
  },
};

{
  "generation_config": {
    "transcription_config": {
      "custom_vocabulary": ["Gemini"],
      "mode": {
        "type": "verbatim",
        "diarization_mode": "speaker",
        "timestamp_granularities": ["word"]
      }
    }
  }
}

interaction = client.interactions.create(
    model="gemini-3.5-transcribe",
    input=[
        {
            "type": "audio",
            "uri": audio_file.uri,
            "mime_type": audio_file.mime_type,
        }
    ],
    generation_config={
        "transcription_config": {
            "mode": {
                "type": "smart",
            },
        }
    },
)
print(interaction.output_text)

const interaction = await client.interactions.create({
  model: "gemini-3.5-transcribe",
  input: [
    {
      type: "audio",
      uri: audioFile.uri,
      mime_type: audioFile.mimeType,
    },
  ],
  generation_config: {
    transcription_config: {
      mode: {
        type: "smart",
      },
    },
  },
});
console.log(interaction.output_text);

curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-3.5-transcribe",
    "input": [
      {
        "type": "audio",
        "uri": "YOUR_FILE_URI",
        "mime_type": "audio/mp3"
      }
    ],
    "generation_config": {
      "transcription_config": {
        "mode": {
          "type": "smart"
        }
      }
    }
  }'

def extract_word_annotations(interaction):
    words = []
    for step in getattr(interaction, "steps", []) or []:
        for content in getattr(step, "content", []) or []:
            for annotation in getattr(content, "annotations", []) or []:
                if getattr(annotation, "type", None) == "word_info":
                    words.append(annotation)
    return words

words = extract_word_annotations(interaction)

for w in words:
    speaker = f"[{w.speaker}] " if getattr(w, "speaker", None) else ""
    start = getattr(w, "start_offset", "")
    end = getattr(w, "end_offset", "")
    timing = f"({start} -> {end}) " if start and end else ""
    print(f"{speaker}{timing}{w.text}")

function extractWordAnnotations(interaction) {
  const words = [];
  for (const step of interaction.steps ?? []) {
    for (const content of step.content ?? []) {
      for (const annotation of content.annotations ?? []) {
        if (annotation.type === "word_info") {
          words.push(annotation);
        }
      }
    }
  }
  return words;
}

const words = extractWordAnnotations(interaction);

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

{
  "id": "interactions/abc123xyz",
  "status": "completed",
  "steps": [
    {
      "id": "step_001",
      "type": "model_output",
      "content": [
        {
          "type": "text",
          "text": "Hello world",
          "annotations": [
            {
              "type": "word_info",
              "text": "Hello",
              "speaker": "spk_1",
              "start_offset": "0.100s",
              "end_offset": "0.450s"
            },
            {
              "type": "word_info",
              "text": "world",
              "speaker": "spk_1",
              "start_offset": "0.500s",
              "end_offset": "0.850s"
            }
          ]
        }
      ]
    }
  ]
}