microsoft / microsoft/BotFramework-WebChat

OpenAI Whisper streaming STT and TTS support

Open
#5,313 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Bot Services customer-reported feature-request
Dominant language
HTML
Stars
1.8k
Forks
1.6k
Avg merge
22h 58m
Merged PRs (30d)
2

Description

Is your feature request related to a problem?

Azure Speech is not as good as Whisper. Webchat with Azure Speech has some misunderstanding problem, very robotic and I cannot customize speech with my voice commands. We need better speech support and Whisper seems better than Azure Speech and the others.

Describe the suggestion or request in detail

Please add streaming Whisper support for both STT and TTS for WebChat. You can provide Whisper Speech on Azure and on a custom on-premise server. Both is required.

Describe alternatives you have considered

No response

Additional context

No response

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

No files or tests are named. Start by locating WebChat’s existing Azure Speech integration and its voice input/output pipeline, then determine how streaming providers are configured. Done would mean supporting Whisper streaming for both STT and TTS through Azure and a custom on-premise server.

Written by the indexing model from the issue text.

Assessment

Tech stack
azure
Domain
audio-video-rtc, frontend
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
30/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.