The TTS feature in the chart section works well, it splits the response by punctuation or paragraph and sends them one at a time. However, with voice calling, after receiving and splitting the response, it sends multiple requests at once, which exceeds my API's concurrency limit. Is there any way to make it send the requests one by one, like it does in the chart section?
Originally created by @louie-studio on GitHub (Feb 25, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/10759
I'm using Docker version v0.5.16.
The TTS feature in the chart section works well, it splits the response by punctuation or paragraph and sends them one at a time. However, with voice calling, after receiving and splitting the response, it sends multiple requests at once, which exceeds my API's concurrency limit. Is there any way to make it send the requests one by one, like it does in the chart section?
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.
Originally created by @louie-studio on GitHub (Feb 25, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/10759
I'm using Docker version v0.5.16.
The TTS feature in the chart section works well, it splits the response by punctuation or paragraph and sends them one at a time. However, with voice calling, after receiving and splitting the response, it sends multiple requests at once, which exceeds my API's concurrency limit. Is there any way to make it send the requests one by one, like it does in the chart section?