Folders and files

Name		Name	Last commit message	Last commit date
Latest commit History 106 Commits
.github		.github
docs		docs
examples		examples
src		src
.YANDEX_PRIVATE_KEY.txt.gpg		.YANDEX_PRIVATE_KEY.txt.gpg
.gitignore		.gitignore
.pyup.yml		.pyup.yml
.readthedocs.yaml		.readthedocs.yaml
LICENSE.txt		LICENSE.txt
README.md		README.md
pyproject.toml		pyproject.toml
requirements.txt		requirements.txt
setup.cfg		setup.cfg

Repository files navigation

🎙 Yandex SpeechKit Python SDK

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 visitYandex Speechkit API Docs. This libsupports short and long audio recognition with speechkit

🛠 Getting Started

Assuming that you have Python andvirtualenv installed, set up your environment and install the required dependencieslike this, or you can install the library usingpip:

$ 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 outspeechkit docs for moreinfo.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:

fromspeechkitimportSessionoauth_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 (readDocumentation for more info):Speechkit.auth.generate_jwt,speechkit.auth.get_iam_token,speechkit.auth.get_api_key

For audio recognition

Short audio:

fromspeechkitimportShortAudioRecognitionrecognizeShortAudio=ShortAudioRecognition(session)withopen(str('/Users/tikhon/Desktop/out.wav'),str('rb'))asf:data=f.read()print(recognizeShortAudio.recognize(data,format='lpcm',sampleRateHertz='48000'))# Will be printed: 'text that need to be recognized'

Look at example with longaudiolong_audio_recognition.py.

Look at example with streamingaudiostreaming_recognize.py

For synthesis

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