Contact UsGet started
© 2025 Direct Cursus Technology L.L.C.

Getting started with Yandex SpeechSense

Written by
Updated at September 5, 2025

Yandex SpeechSense allows you to analyze your business communication channels based on dialog audio recordings or text chat messages and supports integration with your PBX and CRM systems. SpeechSense utilizes Yandex SpeechKit voice technologies to transcribe speech and perform statistical and qualitative analysis of recorded audio dialogs.

SpeechSense can analyze audio and text dialogs in Russian and Kazakh.

You can upload your data to SpeechSense or use a demo recording synthesized using SpeechKit.

Getting started

  1. Navigate to the management console and either log in to Yandex Cloud or sign up if you do not have an account yet. For information on how to get started with Yandex Cloud, see Getting started with Yandex Cloud.

  2. Accept the user agreement.

  3. In Yandex Cloud Billing, make sure you have a billing account linked and its status is ACTIVE or TRIAL_ACTIVE. If you do not have a billing account yet, create one.

  4. Assign the speech-sense.spaces.creator role to your Yandex Cloud account.

    Note

    If you are unable to manage roles, contact your cloud or organization administrator.

  5. Open the SpeechSense home page.

  6. Select the organization to work with SpeechSense in or create a new one.

Set up your environment

  1. Create a space to store all your projects: select Create space, enter a name, add a description if required, and click Create.

  2. Link a billing account to the space. This account will be debited for the use of SpeechSense.

    Note

    The user must have the billing.accounts.editor, billing.accounts.admin, or billing.accounts.owner role for the billing account to manage it.

  3. Navigate to the Connections tab and create a connection based on the metainformation of your audio recordings or text chats:

    1. Specify Connection name.
    2. Select the Two-channel audio, Single-channel audio, or Сhat data type.
    3. Set the connection parameters. For more information, see Creating a connection.
    4. Click Create connection.
    Example of metadata.json for loading audio data

    The dates are ISO 8601 UTC with zero time offset. For Moscow time, add +03:00 instead of Z at the end of the line: 2025-04-24T14:34:19+03:00.

    {
   "direction_outgoung": "true",
   "client_id": "456",
   "client_name": "John Doe",
   "date": "2023-09-29T09:08:38.958Z",
   "date_to": "2023-09-29T09:15:07.897Z",
   "language": "RU",
   "operator_id": "123",
   "operator_name": "Jane Doe"
}

  4. Create a project by clicking Create project on the space page, entering a name for the project, and adding a connection to it. For each connection, you can select filtering rules based on its metainformation and the YandexGPT Pro criteria. With filters, you can ensure that only the dialogs you need are added to the project. After adding all required connections and configuring filters, click Create project.

Upload your data

SpeechSense uses the gRPC API to upload data.

To upload data:

  1. Create a service account.

  2. Add the service account to the namespace with the speech-sense.data.editor role. To learn more about the roles available in the service, see Access management in SpeechSense.

  3. Create an API key or IAM token for the service account to authenticate with the API. Learn more about authentication in the SpeechSense API.

  4. Upload your audio data (split or not split into chunks) or chat history data using a Python data transfer script.

    Use one message for the whole audio.

    SpeechSense supports the following audio file formats:

    • LPCM: AUDIO_ENCODING_LINEAR16_PCM
    • WAV: CONTAINER_AUDIO_TYPE_WAV
    • OggOpus: CONTAINER_AUDIO_TYPE_OGG_OPUS
    • MP3: CONTAINER_AUDIO_TYPE_MP3

    Maximum audio duration is 4 hours.

Next
All guides