Tetap teratur dengan koleksi
Simpan dan kategorikan konten berdasarkan preferensi Anda.
Mentranskripsikan speech to text dengan menggunakan konsol Google Cloud
Panduan memulai ini memperkenalkan Konsol Cloud Speech-to-Text. Dalam panduan memulai ini, Anda akan membuat dan meningkatkan transkripsi serta mempelajari cara menggunakan konfigurasi ini dengan Speech-to-Text API untuk aplikasi Anda sendiri.
Untuk mempelajari cara mengirim permintaan dan menerima respons menggunakan REST API, bukan Konsol, lihat halaman sebelum memulai.
Sebelum memulai
Sebelum dapat mulai menggunakan Konsol Speech-to-Text, Anda harus mengaktifkan API di Google Cloud Platform Console. Langkah-langkah di bawah ini akan memandu Anda melakukan
tindakan berikut:
Mengaktifkan Speech-to-Text di sebuah project.
Pastikan penagihan diaktifkan untuk Speech-to-Text.
Anda dapat memilih project yang sudah ada atau membuat project baru. Untuk mengetahui detail selengkapnya tentang cara membuat project, lihat dokumentasi Google Cloud Platform.
Jika membuat project baru, Anda akan diminta untuk menautkan akun penagihan ke project ini. Jika menggunakan project yang sudah ada, pastikan Anda telah mengaktifkan penagihan.
Setelah memilih project dan menautkannya ke akun penagihan, Anda dapat mengaktifkan Speech-to-Text API. Buka kotak Search products and resources di bagian atas halaman dan ketik "speech".
Pilih Cloud Speech-to-Text API dari daftar hasil.
Untuk mencoba Speech-to-Text tanpa menautkannya ke project Anda, pilih opsi TRY THIS API. Untuk mengaktifkan Speech-to-Text API agar dapat digunakan dengan project Anda, klik ENABLE.
Membuat transkripsi
Izin yang diperlukan untuk langkah ini
Untuk melakukan tugas ini, Anda harus memiliki izin berikut:
storage.buckets.get
storage.buckets.list
storage.buckets.update
Di tingkat project atau bucket:
storage.objects.create
storage.objects.delete
storage.objects.get
storage.objects.list
storage.objects.update
Gunakan konsol Google Cloud untuk membuat transkripsi baru:
Jika ini pertama kalinya Anda menggunakan konsol, Anda akan diminta untuk memilih lokasi penyimpanan konfigurasi dan transkripsi di Cloud Storage.
Di halaman Create transcription, Upload file audio sumber.
Anda dapat memilih file yang telah disimpan di Cloud Storage atau mengupload file baru ke tujuan Cloud Storage yang ditentukan.
Pilih jenis encoding file audio yang diupload.
Tentukan frekuensi sampel.
Klik Lanjutkan. Anda akan diarahkan ke Transcription options.
Opsi transkripsi
Pilih kode bahasa audio sumber Anda. Ini adalah bahasa yang
sedang diucapkan dalam rekaman.
Pilih model transkripsi yang ingin Anda gunakan pada file.
Opsi Default telah dipilih sebelumnya dan, umumnya, tidak diperlukan perubahan,
tetapi mencocokkan model dengan jenis audio dapat menghasilkan akurasi yang lebih tinggi.
Perhatikan bahwa biaya model bervariasi.
Klik Lanjutkan. Anda akan diarahkan ke Model adaptation.
Adaptasi model (opsional)
Jika audio sumber berisi hal-hal seperti kata-kata yang langka, nama diri, atau
istilah kepemilikan eksklusif dan Anda mengalami masalah dengan pengenalan, adaptasi
model dapat membantu.
Centang Aktifkan adaptasi model.
Pilih Resource adaptasi sekali pakai.
Tambahkan frasa yang relevan dan beri nilai peningkatan.
Di kolom sebelah kiri, klik Kirim untuk membuat transkripsi.
Tinjau transkripsi Anda
Bergantung pada ukuran file audio Anda, pembuatan transkripsi dapat memerlukan waktu beberapa menit hingga jam. Setelah dibuat, transkripsi Anda siap untuk
ditinjau. Mengurutkan tabel berdasarkan stempel waktu dapat membantu Anda menemukan transkripsi terbaru dengan mudah.
Klik Nama transkripsi yang ingin ditinjau.
Bandingkan teks Transkripsi dengan file audio
Jika Anda ingin melakukan perubahan, klik Gunakan kembali konfigurasi.
Tindakan ini akan membawa Anda ke alur Buat transkripsi dengan opsi
yang sama yang telah dipilih sebelumnya, sehingga Anda dapat mengubah beberapa hal, membuat transkripsi
baru, dan membandingkan hasilnya.
[[["Mudah dipahami","easyToUnderstand","thumb-up"],["Memecahkan masalah saya","solvedMyProblem","thumb-up"],["Lainnya","otherUp","thumb-up"]],[["Sulit dipahami","hardToUnderstand","thumb-down"],["Informasi atau kode contoh salah","incorrectInformationOrSampleCode","thumb-down"],["Informasi/contoh yang saya butuhkan tidak ada","missingTheInformationSamplesINeed","thumb-down"],["Masalah terjemahan","translationIssue","thumb-down"],["Lainnya","otherDown","thumb-down"]],["Terakhir diperbarui pada 2025-08-18 UTC."],[],[],null,["# Quickstart: Transcribe speech to text by using the Google Cloud console\n\nTranscribe speech to text by using the Google Cloud console\n===========================================================\n\nThis quickstart introduces you to the\n[Cloud Speech-to-Text Console](https://console.cloud.google.com/speech). In this\nquickstart, you will create and refine a transcription and learn how to\nuse this configuration with the Speech-to-Text API for your own applications.\n\nTo learn how to send requests and receive responses using the REST API instead\nof the Console, see the\n[before you begin](/speech-to-text/docs/before-you-begin) page.\n\nBefore you begin\n----------------\n\nBefore you can begin using the Speech-to-Text Console, you must enable the\nAPI in the Google Cloud Platform Console. The steps below walk you through the\nfollowing actions:\n\n- Enable Speech-to-Text on a project.\n- Make sure billing is enabled for Speech-to-Text.\n\n### Set up your Google Cloud project\n\n1. [Sign in to Google Cloud console](https://console.cloud.google.com/)\n\n2. [Go to the project selector page](https://console.cloud.google.com/projectselector2/home/dashboard)\n\n You can either choose an existing project or create a new one. For more details\n about creating a project, see\n [Google Cloud Platform documentation](/resource-manager/docs/creating-managing-projects).\n3. If you create a new project, you will be prompted to link a billing account\n to this project. If you are using a pre-existing project, make sure that you\n have billing enabled.\n\n [Learn how to confirm that billing is enabled for your project](/billing/docs/how-to/modify-project)\n | **Note:** You must enable billing to use Speech-to-Text API, however you will not be charged unless you exceed the free quota. See the [pricing](/speech-to-text/pricing) page for more details.\n4. Once you have selected a project and linked it to a billing account, you\n can enable the Speech-to-Text API. Go to the **Search products and\n resources** bar at the top of the page and type in **\"speech\"**.\n\n5. Select the **Cloud Speech-to-Text API** from the list of results.\n\n6. To try Speech-to-Text without linking it to your project, choose\n the **TRY THIS API** option. To enable the Speech-to-Text API for use\n with your project, click **ENABLE**.\n\nCreate a transcription\n----------------------\n\n#### Permissions required for this task\n\nTo perform this task, you must have the following\n[permissions](/iam/docs/overview#permissions):\n\n\n- `storage.buckets.get`\n- `storage.buckets.list`\n- `storage.buckets.update`\n\nAt the project or bucket level:\n\n- `storage.objects.create`\n- `storage.objects.delete`\n- `storage.objects.get`\n- `storage.objects.list`\n- `storage.objects.update`\n\nUse the Google Cloud console to create a new transcription:\n\n### Audio configuration\n\n1. Open the [**Speech-to-Text** overview](https://console.cloud.google.com/speech).\n\n \u003cbr /\u003e\n\n2. Click **Create transcription**.\n\n - If this is your first time using the console, you will be asked to choose where in Cloud Storage to store your configurations and transcriptions.\n3. In the **Create transcription** page, **Upload a source audio file**.\n You can choose a file that is already saved in Cloud Storage or upload a\n new one to your specified Cloud Storage destination.\n\n4. Select the uploaded audio file's **encoding type**.\n\n5. Specify its **sample rate**.\n\n6. Click **Continue** . You will be taken to **Transcription options**.\n\n### Transcription options\n\n1. Select the **language code** of your source audio. This is the language\n being spoken in the recording.\n\n2. Choose the **transcription model** you would like to use on the file.\n The Default option is pre-selected and, generally, no change is needed,\n but matching the model to the type of audio may result in higher accuracy.\n Note that model costs vary.\n\n \u003cbr /\u003e\n\n3. Click **Continue** . You will be taken to **Model adaptation**.\n\n### Model adaptation (optional)\n\nIf your source audio contains things like rare words, proper names, or\nproprietary terms and you experience problems with recognition, model\nadaptation can help.\n\n1. Check **Turn on model adaptation**.\n\n2. Choose **One-time adaptation resource**.\n\n3. Add relevant **phrases** and give them a **boost value**.\n\n \u003cbr /\u003e\n\n4. In the left column, click **Submit** to create your transcription.\n\n### Review your transcription\n\nDepending on the size of your audio file, a transcription may take from minutes\nto hours to create. Once your transcription has been created, it's ready for\nreview. Sorting the table by timestamp can help you easily locate your recent\ntranscriptions.\n\n1. Click on the **Name** of the transcription you would like to review.\n\n2. Compare the **Transcription** text to the audio file\n\n3. If you would like to make changes, click **Reuse configuration** .\n This will bring you to the **Create transcription** flow with the same\n options pre-selected, allowing you to change a few things, create a new\n transcription, and compare the results.\n\nWhat's next\n-----------\n\n\n- Practice [transcribing short audio files](/speech-to-text/docs/sync-recognize).\n- Learn how to [batch long audio files for speech recognition](/speech-to-text/docs/async-recognize).\n- Learn how to [transcribe streaming audio](/speech-to-text/docs/streaming-recognize) like from a microphone.\n- Get started with the Speech-to-Text in your language of choice by using a [Speech-to-Text client library](/speech-to-text/docs/reference/libraries).\n- Work through the [sample applications](/speech-to-text/docs/samples).\n- For best performance, accuracy, and other tips, see the [best practices](/speech-to-text/docs/best-practices) documentation.\n\n\u003cbr /\u003e"]]
