
Lets your agent write Python code for Azure speech-to-text, batch and real-time
- Open source
- 3.2K GitHub stars
- Design and media


Lets your agent write Python code for Azure speech-to-text, batch and real-time

Generates narration, voiceover and IVR audio with OpenAI text-to-speech via a bundled CLI

Transcribes short audio files to text with Azure's Speech REST API, no SDK needed

Generates spoken podcast-style narratives from text using Azure OpenAI GPT Realtime Mini

Run Gemini API calls from the shell for media generation, file analysis and transcription

Build real-time bidirectional voice AI apps in Python with Azure AI Voice Live

Builds and fixes NVIDIA speech-to-speech voice agents on Pipecat or LiveKit

Turns raw videos into chain-of-thought QA training data using VLM and LLM teacher models

Lets your agent run cloud media jobs: encode video, resize images, extract audio, OCR

Turns written text or summaries into a listenable MP3 using local neural speech

Runs InternVideo2-CLIP video-text retrieval, fine-tuning, ONNX export and TensorRT deploy

Extracts text, tables, transcripts and fields from documents, images, audio and video
The closest alternatives to Transcribe are Azure AI transcription py, Speech, Azure speech to text REST py, Podcast generation and Gemini API CLI.
Yes. Azure AI transcription py, Speech, Azure speech to text REST py have a free or open-source option.