Python SDK for Yandex SpeechKit API. This SDK allows you to use the cloud API for speech recognition and synthesis from Yandex.

For more information please visit Yandex Speechkit API Docs. This lib supports short and long audio recognition with speechkit

🛠 Getting Started

Assuming that you have Python and virtualenv installed, set up your environment and install the required dependencies like this, or you can install the library using pip:

$ git clone https://github.com/TikhonP/yandex-speechkit-lib-python.git
$ cd yandex-speechkit-lib-python
$ virtualenv venv
...
$ . venv/bin/activate
$ python -m pip install -r requirements.txt
$ python -m pip install .

python -m pip install speechkit

📑 Speechkit documentation

Check out speechkit docs for more info. PDF docs

🔮 Using speechkit

There are support of recognizing long and short audio and synthesis. For more information please read docs below.

First you need create session for authorisation:

from speechkit import Session

oauth_token = str('<oauth_token>')
folder_id = str('<folder_id>')
api_key = str('<api-key>')
jwt_token = str('<jwt_token>')

oauth_session = Session.from_yandex_passport_oauth_token(oauth_token, folder_id)
api_key_session = Session.from_api_key(api_key, x_client_request_id_header=True, x_data_logging_enabled=True) 
# You can use `x_client_request_id_header` and `x_data_logging_enabled` params to troubleshoot yandex recognition
# Use `Session.get_x_client_request_id()` method to get x_client_request_id value.
jwt_session = Session.from_jwt(jwt_token)

Use created session to make other requests.

There are also functions for getting credentials (read Documentation for more info): Speechkit.auth.generate_jwt, speechkit.auth.get_iam_token, speechkit.auth.get_api_key

For audio recognition

Short audio:

from speechkit import ShortAudioRecognition

recognizeShortAudio = ShortAudioRecognition(session)
with open(str('/Users/tikhon/Desktop/out.wav'), str('rb')) as f:
    data = f.read()

print(recognizeShortAudio.recognize(data, format='lpcm', sampleRateHertz='48000'))

# Will be printed: 'text that need to be recognized'

Look at example with long audio long_audio_recognition.py .

Look at example with streaming audio streaming_recognize.py

For synthesis

from speechkit import SpeechSynthesis

synthesizeAudio = SpeechSynthesis(session)
synthesizeAudio.synthesize(
    str('/Users/tikhon/Desktop/out.wav'), text='Text that will be synthesised',
    voice='oksana', format='lpcm', sampleRateHertz='16000'
)

🔗 Links

• Readthedocs Documentation for this package
• Yandex Speechkit Documentation
• Статья на хабре

💼 License

MIT

In other words, you can use the code for private and commercial purposes with an author attribution (by including the original license file).

Feel free to contact us via email tikhon.petrishchev@gmail.com.

❤️