STT
Note
Currently, there are two UIs that support Workflows: Yandex Cloud
- Workflows created in the Yandex Cloud UI are automatically available in the AI Studio UI.
- Workflows created in the AI Studio UI are not available in the Yandex Cloud UI.
Starting September 3, 2026, Workflows will no longer be supported in the Yandex Cloud UI. To create and manage workflows, use the AI Studio UI.
Speech recognition in audio files using Yandex SpeechKit STT
The base64, url, objectStorage, and disk fields are mutually exclusive: you can use only one of them.
| Field name | Type | Required | Default value | Templating supported | Description |
|---|---|---|---|---|---|
recognizeText |
STT.RecognizeText | Yes | None | None | Speech recognition settings. |
base64 |
string |
None | None | Yes | Base64-encoded audio file. |
url |
string |
None | None | Yes | Audio file via a public URL. |
objectStorage |
STT.ObjectStorage | None | None | None | Audio file from an Object Storage bucket. |
disk |
STT.Disk | None | None | None | Audio file on Yandex Disk. |
STT.RecognizeText
|
Field name |
Type |
This is a required field |
Default value |
Templating supported |
Description |
|
|
|
Yes |
None |
None |
Audio file format. Available formats: |
|
|
|
Yes |
None |
None |
Speech recognition languages. Available languages
|
|
|
|
Yes |
None |
None |
Speech recognition model. Available model: |
STT.ObjectStorage
| Field name | Type | Required | Default value | Templating supported | Description |
|---|---|---|---|---|---|
bucket |
string |
Yes | None | None | Name of the Object Storage bucket the audio file is in. |
object |
string |
Yes | None | Yes | Object name, e.g., prefix/subprefix/data.mp3. |
STT.Disk
| Field name | Type | Required | Default value | Templating supported | Description |
|---|---|---|---|---|---|
oauthToken |
string |
Yes | None | None | OAuth token |
path |
string |
Yes | None | Yes | Audio file path. |
sharedDiskId |
string |
None | None | Yes | Shared disk label |