Yandex Cloud
Search
Contact UsGet started
  • Blog
  • Pricing
  • Documentation
  • All Services
  • System Status
    • Featured
    • Infrastructure & Network
    • Data Platform
    • Containers
    • Developer tools
    • Serverless
    • Security
    • Monitoring & Resources
    • ML & AI
    • Business tools
  • All Solutions
    • By industry
    • By use case
    • Economics and Pricing
    • Security
    • Technical Support
    • Customer Stories
    • Start testing with double trial credits
    • Cloud credits to scale your IT product
    • Gateway to Russia
    • Cloud for Startups
    • Education and Science
    • Yandex Cloud Partner program
  • Blog
  • Pricing
  • Documentation
© 2025 Direct Cursus Technology L.L.C.
Yandex SpeechSense
  • Getting started
    • Resource hierarchy
    • Dialogs
    • Dialog tags
    • Dictionaries for tags
    • Supported audio formats
    • Quotas and limits
  • Audit Trails events
  • Access management
  • Pricing policy
  • Release notes
  • FAQ

In this article:

  • LPCM
  • WAV
  • MP3
  • OggOpus
  1. Concepts
  2. Supported audio formats

Supported audio formats

Written by
Yandex Cloud
Updated at April 30, 2025
  • LPCM
  • WAV
  • MP3
  • OggOpus

SpeechSense allows you to upload audio files in these formats:

  • LPCM
  • WAV
  • MP3; preferred format
  • OggOpus

LPCMLPCM

Linear pulse-code modulation is a format of uncompressed audio encoding.

LPCM audio requirements:

  • Sampling rate: Between 8 kHz and 48 kHz.
  • Bit depth: 16 bit.
  • Byte order: Reversed (little-endian).
  • Audio data is stored as signed integers.

WAVWAV

For WAV, data is encoded using LPCM and packaged in a WAV container.

LPCM format requirements also apply to WAV audio files. SpeechSense only recognizes WAV if the audio files use the LPCM encoding and comply with the format requirements.

MP3MP3

For MP3, data is encoded using the MPEG-1/2/2.5 Layer III audio codec and packaged in an MP3 container.

SpeechSense recognizes MP3 without audio file quality and header restrictions.

OggOpusOggOpus

For OggOpus, data is encoded using the OPUS audio codec and compressed using the OGG container format.

SpeechSense recognizes OggOpus without audio file quality and header restrictions.

Was the article helpful?

Previous
Semantic attributes
Next
Quotas and limits
© 2025 Direct Cursus Technology L.L.C.