8000 Fatal Error when interrupting OpenAIRealtimeBetaLLMService during speech · Issue #1963 · pipecat-ai/pipecat · GitHub
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content

Fatal Error when interrupting OpenAIRealtimeBetaLLMService during speech #1963

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom
Open
NicolaiMinter opened this issue Jun 5, 2025 · 0 comments
Open

Fatal Error when interrupting OpenAIRealtimeBetaLLMService during speech #1963

NicolaiMinter opened this issue Jun 5, 2025 · 0 comments

Comments

@NicolaiMinter
Copy link

pipecat version

0.0.67

Python version

3.13.3

Operating System

macOS 15.5

Issue description

When using OpenAIRealtimeBetaLLMService, a Fatal Error occurs if I start speaking while the bot is still speaking, but only after a function call has previously been executed. I encounter two different erros, see logs below.

Reproduction steps

  1. Use the voice-based OpenAIRealtimeBetaLLMService.
  2. Trigger a prompt that causes the model to make a function call.
  3. Let the bot start speaking the response.
  4. While the bot is still speaking, start speaking yourself (i.e., interrupt via voice).
  5. Observe a Fatal Error.

Expected behavior

No fatal error occurs

Actual behavior

fatal error occurs

Logs

Error 1: A fatal error occurred: ErrorFrame#1(error: The server had an error while processing your request. Sorry about that! Please contact us through our help center at help.openai.com if the error persists. (include session ID in your message: ***). We recommend you retry your request., fatal: True)

Error 2: A fatal error occurred: ErrorFrame#0(error: Error: event_id='***' type='error' error=RealtimeError(type='invalid_request_error', code='invalid_value', message='Audio content of 6100ms is already shorter than 6185ms', param=None, event_id=None), fatal: True)
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@NicolaiMinter
0