azure-speech-to-text-rest-py

To transcribe audio, send WAV or OGG files up to 60 seconds directly to the Azure Speech to Text REST API using Python requests. The Skill handles HTTP POST requests and returns text in simple or detailed JSON format.

No, transcribing audio does not require installing the Azure Speech SDK. This Skill uses the Python requests library to call the Azure Speech to Text REST API directly, needing only an Azure subscription, Speech resource, and API key.

WAV and OGG audio formats are supported for speech to text transcription via the REST API. The Python Skill processes these formats and returns text in simple or detailed JSON output configurations.

Yes, chunked transfer encoding is supported for lower latency during audio transcription. The Skill allows chunked data transfer to the Azure Speech to Text REST API, minimizing delay when processing WAV or OGG audio files.

The maximum audio length for REST API transcription is 60 seconds. This Skill transcribes short audio files like voice memos or call snippets using Python requests and the Azure Speech to Text REST API.

Select between simple or detailed JSON output options to configure the audio transcription response. The Skill requests the chosen format from the Azure Speech to Text REST API, returning either basic text or detailed metadata in JSON.