Skip to content

Navigation Menu

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

Appearance settings

gpt-4o-mini-realtime-preview unable to respond with realtime audio #2352

Copy link
Copy link
Closed
@jverkoey

Description

@jverkoey
Issue body actions

Confirm this is an issue with the Python library and not an underlying OpenAI API

  • This is an issue with the Python library

Describe the bug

The following initialization works and results in a realtime audio conversation:

async with client.beta.realtime.connect(model="gpt-4o-realtime-preview-2024-12-17") as openai_stream:

But when I try to use gpt-4o-mini, like so:

async with client.beta.realtime.connect(model="gpt-4o-mini-realtime-preview") as openai_stream:

I get the following errors after speaking:

{ 'event_id': 'event_BVkCL9CtzRVz1CIrI1jNe',
  'response': { 'conversation_id': 'conv_BVkC88oBioiBmAEr6RYBn',
                'id': 'resp_BVkCLamsLeAeHny8E3f1L',
                'max_output_tokens': 4096,
                'metadata': None,
                'modalities': ['text', 'audio'],
                'object': 'realtime.response',
                'output': [],
                'output_audio_format': 'pcm16',
                'status': 'failed',
                'status_details': { 'error': { 'code': None,
                                               'message': '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: '
                                                          'sess_BVkC8iXlHg3H71vTbI9Te). We '
                                                          'recommend you retry your request.',
                                               'type': 'server_error'},
                                    'reason': None,
                                    'type': 'failed'},
                'temperature': 0.8,
                'usage': { 'input_token_details': { 'audio_tokens': 0,
                                                    'cached_tokens': 0,
                                                    'cached_tokens_details': { 'audio_tokens': 0,
                                                                               'text_tokens': 0},
                                                    'text_tokens': 0},
                           'input_tokens': 0,
                           'output_token_details': {'audio_tokens': 0, 'text_tokens': 0},
                           'output_tokens': 0,
                           'total_tokens': 0},
                'voice': 'verse'},
  'type': 'response.done'}

To Reproduce

async with client.beta.realtime.connect(model="gpt-4o-mini-realtime-preview") as openai_stream:

Code snippets

OS

macOS

Python version

3.13

Library version

1.78.0

Metadata

Metadata

Assignees

No one assigned

    Labels

    bugSomething isn't workingSomething isn't working

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions

      Morty Proxy This is a proxified and sanitized view of the page, visit original site.