dwani 0.1.5

Multimodal API for Indian languages (speech, vision, LLMs, TTS, ASR, etc.)

dwani.ai - python library

Install the library

pip install dwani

Setup the credentials

import dwani
import os

dwani.api_key = os.getenv("DWANI_API_KEY")

dwani.api_base = os.getenv("DWANI_API_BASE_URL")

Examples

Text Query

resp = dwani.Chat.create(prompt="Hello!", src_lang="eng_Latn", tgt_lang="kan_Knda")
print(resp)

Vision Query

result = dwani.Vision.caption(
    file_path="image.png",
    query="Describe this logo",
    src_lang="eng_Latn",
    tgt_lang="kan_Knda"
)
print(result)

Speech to Text - Automatic Speech Recognition (ASR)

result = dwani.ASR.transcribe(file_path="kannada_sample.wav", language="kannada")
print(result)

Text to Speech - Speech Synthesis

response = dwani.Audio.speech(input="ಕರ್ನಾಟಕ ದ ರಾಜಧಾನಿ ಯಾವುದು", response_format="mp3")
with open("output.mp3", "wb") as f:
    f.write(response)

• Website -> dwani.ai

Contact

• For any questions or issues, please open an issue on GitHub or contact us via email.
• For collaborations
  • Join the discord group - invite link