feat(voice_agent): support voice agent in AgentScope

[DavdGao]

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

[github-actions]

This issue is marked as stale because there has been no activity for 21 days. Remove stale label or add new comments or this issue will be closed in 3 day.

[github-actions]

Close this stale issue.

[github-actions]

This issue is marked as stale because there has been no activity for 21 days. Remove stale label or add new comments or this issue will be closed in 3 day.