Feature Request: Implement OpenAPI's streaming text to speech protocol for /v1/audio/transcriptions

[candrews]

Prerequisites

• I am running the latest code. Mention the version if possible as well.
• I carefully followed the README.md.
• I searched using keywords relevant to my issue to make sure that I am creating a new issue that is not already open (or closed).
• I reviewed the Discussions, and have a new and useful enhancement to share.

Feature Description

OpenAI specifies a protocol for speech to text streaming transcription with /v1/audio/transcriptions, see "Streaming the transcription of a completed audio recording" at https://developers.openai.com/api/docs/guides/speech-to-text#streaming-the-transcription-of-a-completed-audio-recording

The implementation of OAI STT in llama.cpp, added in #21863 by @ngxson, doesn't support streaming. This feature request is for adding streaming support.

Motivation

By implementing the OpenAI streaming STT protocol, many existing clients will be able to leverage this feature. For example, I'm particularly interested in enabling Wyoming OpenAI's streaming support which will improve the responsiveness of Home Assistant voice assistants.

Possible Implementation

No response

[github-actions]

This issue was closed because it has been inactive for 14 days since being marked as stale.