-
Notifications
You must be signed in to change notification settings - Fork 2.4k
feat(voice_agent): support voice agent in AgentScope #773
Copy link
Copy link
Closed
Labels
RoadmapThe development planThe development planstate: in progressWorking in progressWorking in progress
Description
Support voice agent in three steps:
- Support TTS models
- Support TTS model feat(tts): implement tts #965
- Support to filter text (e.g. markdown)
- [TBD] If we need to support the incremental output from TTS model
- Support multimodal models
- Support omini model in DashScope API Support omni series model #759
- Support gpt-audio model in OpenAI API
- [Abandoned] Support audio input in the UserAgent class
- Support realtime models feat(voice_agent): support voice agent in AgentScope #773
- Support omini-realtime API
- Support realtime API of OpenAI API
Reactions are currently unavailable
Metadata
Metadata
Assignees
Labels
RoadmapThe development planThe development planstate: in progressWorking in progressWorking in progress
Type
Projects
Status
Done