Tinkoff Python VoiceKit API Library

Usage

Install from PyPi

pip install tinkoff-voicekit-ai

Common

Before using you must have API_KEY and SECRET_KEY. You can get the keys by leaving a request on our website.

Documentation

Type schema

Examples of using VoiceKit client:

• Recognition examples
• Synthesize examples
• Operation examples
• Uploader examples

Call documentation for public methods

from tinkoff_voicekit_ai import ClientSTT

API_KEY = "my_api_key"
SECRET_KEY = "my_secret_key"

client = ClientSTT(API_KEY, SECRET_KEY)

client.something_method.__doc__

Methods initialize using config (Python dict) which satisfies one of the next json schema.

Recogniton (STT)

Example of using STT

• recognize

from tinkoff_voicekit_ai import ClientSTT

API_KEY = "my_api_key"
SECRET_KEY = "my_secret_key"

client = ClientSTT(API_KEY, SECRET_KEY)

audio_config = {
    "encoding": "LINEAR16",
    "sample_rate_hertz": 8000,
    "num_channels": 1
}

# recognise method call
response = client.recognize("path/to/audio/file", audio_config)
print(response)

• streaming recognize

from tinkoff_voicekit_ai import ClientSTT

API_KEY = "my_api_key"
SECRET_KEY = "my_secret_key"

client = ClientSTT(API_KEY, SECRET_KEY)

audio_config = {
    "encoding": "LINEAR16",
    "sample_rate_hertz": 8000,
    "num_channels": 1
}
stream_config = {"config": audio_config}

# recognise stream method call
with open("path/to/audio/file", "rb") as source:
    responses = client.streaming_recognize(source, stream_config)
    for response in responses:
        print(response)

• long running recognize with uploader

from tinkoff_voicekit_ai import ClientSTT

API_KEY = "my_api_key"
SECRET_KEY = "my_secret_key"

client = ClientSTT(API_KEY, SECRET_KEY)

audio_config = {
    "encoding": "LINEAR16",
    "sample_rate_hertz": 8000,
    "num_channels": 1
}

request = {
    "config": audio_config,
    "group": "group_name"
}

file_path = "path/to/file"
audio_name_for_storage = "pretty name"

# this method automatically upload audio to long running storage and return uri
print(client.longrunning_recognize_with_uploader(file_path, request, audio_name_for_storage))

Example of Voice Activity Detection configuration

vad = {}
vad["min_speech_duration"] = min_speech_duration
vad["max_speech_duration"] = max_speech_duration
vad["silence_duration_threshold"] = silence_duration_threshold
vad["silence_prob_threshold"] = silence_prob_threshold
vad["aggressiveness"] = aggressiveness

my_config = {}
my_config["vad"] = vad

Synthesize (TTS)

Example of input file:

Я жду вашего ответа. Вы готовы сделать перевод?
# Давайте уточним получателя. Как его зовут?

commented lines # will not be synthesis

Example of using TTS

• default

from tinkoff_voicekit_ai import ClientTTS

API_KEY = "api_key"
SECRET_KEY = "secret_key"

client = ClientTTS(API_KEY, SECRET_KEY)
audio_config = {
    "audio_encoding": "LINEAR16",
    "sample_rate_hertz": 48000
}


# use it if you want work with proto results
# audio file
rows_responses = client.streaming_synthesize("path/to/file/with/text", audio_config)
# text
rows_responses = client.streaming_synthesize("Мой красивый текст", audio_config)

# use it if you want get audio file results
# audio file
client.synthesize_to_audio_wav("path/to/file/with/text", audio_config, "output/dir")
# text
client.synthesize_to_audio_wav("Мой красивый текст", audio_config, "output/dir")
# ssml. There are only tag <speak>
client.synthesize_to_audio_wav("<speak>Мой красивый текст</speak>", audio_config, "output/dir", ssml=True)

• change voice

from tinkoff_voicekit_ai import ClientTTS

API_KEY = "api_key"
SECRET_KEY = "secret_key"

client = ClientTTS(API_KEY, SECRET_KEY)
config = {
        "audio_encoding": "RAW_OPUS",
        "sample_rate_hertz": 48000,
        "voice": {"name": "alyona"}
    }
client.synthesize_to_audio_wav("Приве! Меня зовут Алена.", config)

Example of using Operations

• get operation by id

from tinkoff_voicekit_ai import ClientOperations
API_KEY = "my_api_key"
SECRET_KEY = "my_secret_key"

operations = ClientOperations(API_KEY, SECRET_KEY)

running_operation_id = "42"

print(operations.get_operation({"id": running_operation_id}))

• cancel operation by id

from tinkoff_voicekit_ai import ClientOperations
API_KEY = "my_api_key"
SECRET_KEY = "my_secret_key"

operations = ClientOperations(API_KEY, SECRET_KEY)
operation_filter = {"exact_id": "31"}

# return empty dict on success
print(operations.cancel_operation(operation_filter))

Example of using Uploader

from tinkoff_voicekit_ai import Uploader
API_KEY = "my_api_key"
SECRET_KEY = "my_secret_key"

uploader = Uploader(API_KEY, SECRET_KEY)
path = "path/to/file"

print(uploader.upload(path, "object_name"))