رونویسی صوتی

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"],
            },
        }
    },