Skip to main content

Voicegain Speech-to-Text Python SDK

Project description

Voicegain Speech-to-Text Python SDK

Python SDK for the Voicegain Speech-to-Text API.

This API allows for large vocabulary speech-to-text transcription as well as grammar-based speech recognition. Both real-time and offline use cases are supported.

You can see the core Voicegain API documentation here.

The complete documentation for the API covered by this SDK is available here - this link requires an account on the Voicegain portal - see below for how to sign up.

Requirements

In order to use this API you need account with Voicegain. You can create an account by signing up on Voicegain Portal. No credit card required to sign up.

You can see pricing here - basically, it is 1 cent a minute for off-line and 1.25 cents a minute for real-time. There is a Free Tier of 600 minutes that renews each month.

Installation

From PyPI directly:

pip install voicegain-speech

Examples

  • sync_transcribe example:

configuration:

from voicegain_speech import ApiClient
from voicegain_speech import Configuration
from voicegain_speech import TranscribeApi
import base64


# configure your JWT token
JWT = "Your <JWT>"

configuration = Configuration()
configuration.access_token = JWT

api_client = ApiClient(configuration=configuration)

transcribe local file:

transcribe_api = TranscribeApi(api_client)
file_path = "Your local file path"

with open(file_path, "rb") as f:
    audio_base64 = base64.b64encode(f.read()).decode()

response = transcribe_api.asr_transcribe_post(
    sync_transcription_request={
        "audio": {
            "source": {
                "inline": {
                    "data": audio_base64
                }
            }
        }
    }
)

alternatives = response.result.alternatives
if alternatives:
    local_result = alternatives[0].utterance
    print("result from file: ", local_result)

else:
    local_result = None
    print("no transcription")

More examples can be found in examples folder on our GitHub


Learn more about the Voicegain Voice AI Platform at www.voicegain.ai

Project details


Release history Release notifications | RSS feed

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

voicegain-speech-1.100.0.tar.gz (4.5 MB view details)

Uploaded Source

File details

Details for the file voicegain-speech-1.100.0.tar.gz.

File metadata

  • Download URL: voicegain-speech-1.100.0.tar.gz
  • Upload date:
  • Size: 4.5 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/1.15.0 pkginfo/1.9.6 requests/2.31.0 setuptools/59.6.0 requests-toolbelt/1.0.0 tqdm/4.66.1 CPython/3.10.12

File hashes

Hashes for voicegain-speech-1.100.0.tar.gz
Algorithm Hash digest
SHA256 09616e67f4c5a81aad8972deb09fbe81c2826ca42dc61b62ff9a9be25fa8d979
MD5 266c47d8bc7d2b0ec690977f40e26b0f
BLAKE2b-256 04255704014e81621b97caa137fcfdf7c7e024aaf993eb3efc4d90a87e387fdb

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page