Skip to content

An efficient audio transcriber, it works on recaptcha audios.

License

Notifications You must be signed in to change notification settings

claudileij/speechtext.py

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Speechtext.py

Initialization

Clonning speechtext repository:

git clone https://github.com/nxSlayer/speechtext.py.git
cd speechtext.py

Installing the requirements:

pip install -r requirements.txt

Usage

In your project, import the speechtext.py class:

from speechtext import SpeechText

and init this class with api_key argument:

api = SpeechText('your_api_key')

start an task:

file = "your file path, url or bytes"
task = api.startTask(file=file)

print(task.status)
print(task.createdAt)
print(task.id)

# GETTING TASK RESULT
# Obs: time.sleep is recommended

result = api.taskResult(taskId=task.id)
print(result.status) # failed | finished
print(result.remainingSeconds) # int
print(result.transcript) # transcribed text
print(result.word_time_offsets) #list

Get your free api key

Register in speechtext.ai and receive your free trial key in email

Documentation

If you are looking for other solutions, you can look at the [speechtext.ai docs](https://speechtext.ai/speech-api-docs`enter code here`)

About

An efficient audio transcriber, it works on recaptcha audios.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages