Getting started with SpeechKit

You can test speech recognition and synthesis on the SpeechKit demo page. For information on pricing, see SpeechKit pricing policy.

Getting startedGetting started

1. Go to the management console and log in to Yandex Cloud or sign up if not signed up 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.

Speech recognition using PlaygroundSpeech recognition using Playground

To recognize speech from an audiofile via the SpeechKit Playground interface:

1. In the management console, select the folder you are going to use to work with SpeechKit.
2. In the list of services, select SpeechKit.
3. In the window that opens, select the Speech recognition section.
4. In the Language field, select the language you need or leave Automatic.
5. Click Select file or drag the audio file to the loading area.
6. Click Start recognition to start speech recognition in the audio file.

SpeechKit Playground features basic speech recognition options. For more flexible recognition settings, use the API.

Speech synthesis using PlaygroundSpeech synthesis using Playground

To convert text to audio via the SpeechKit Playground interface:

1. In the management console, select the folder you are going to use to work with SpeechKit.
2. In the list of services, select SpeechKit.
3. In the window that opens, select the Speech synthesis section.
4. In the settings section on the left side of the window:
   • Pauses: Select the length of pauses between words or specify it yourself.
   • Emphasize word: Emphasize the essential words.
   • Stress: Mark the stressed vowels to clarify the correct pronunciation of the words.
   • Phonemes: Monitor the correct pronunciation of words using phonemes.
5. Under Synthesis settings on the right side of the window:
   • Language: Select the speaker's language.
   • Voice: Specify the speaker's voice.
   • Role: Select the speaker's role.
   • Speech speed: Set the speaker's speech rate.
   • Voice pitch: Adjust the speaker's voice pitch.
   • Audio format: Select the audio format.
6. Click Synthesize and playback to synthesize speech.
7. To download the result, click .

SpeechKit Playground features basic speech synthesis options. For more flexible synthesis settings, use the API.

Speech recognition via the APISpeech recognition via the API

Learn how to recognize short and long pre-recorded audio files in SpeechKit. The service also supports voice recognition in real time.

Speech synthesis via the APISpeech synthesis via the API

Learn how to convert text to audio using the SpeechKit API v1 and API v3. The API v3 provides more flexibility for speech synthesis setup. For more information about the differences between the API versions, see Synthesis options.

See alsoSee also

• Read more about speech recognition
• Read more about speech synthesis
• Supported audio formats
• Roles required for performing operations
• All SpeechKit integration examples