|
Model gpt-realtime-2.1-mini not calling function tools in SIP Realtime, while gpt-realtime-mini works with the same prompt/tools
|
|
6
|
365
|
October 6, 2026
|
|
GPT-Live-1 Vesper: How Can I Adjust the Accent and Enthusiasm?
|
|
0
|
23
|
October 6, 2026
|
|
Realtime API cost tracking per session
|
|
3
|
617
|
October 6, 2026
|
|
Gpt-live-transcribe: deltas stop mid-item with no event, and audio appended after that is never transcribed
|
|
1
|
42
|
October 5, 2026
|
|
Tool call parameters with descriptions in gpt-live
|
|
1
|
82
|
October 4, 2026
|
|
Important Feedback/improvements for gpt-live-1 API
|
|
3
|
137
|
October 3, 2026
|
|
GPT-Live starts calls talking about a buffet in a strange voice?
|
|
2
|
106
|
October 3, 2026
|
|
Bug Report: gpt-realtime-2 Produces Nonsense Spoken Responses That Are Not Captured in the Logged Transcript
|
|
1
|
258
|
October 2, 2026
|
|
9 voices mentioned in official openai API reference gets rejected by the API
|
|
1
|
101
|
October 2, 2026
|
|
Issues with realtime turn-taking
|
|
5
|
754
|
October 1, 2026
|
|
GPT-Live-1 still struggles with customer names and digit sequences — what works?
|
|
1
|
74
|
October 1, 2026
|
|
Bug Report: Inconsistent speech_started / speech_ended Behavior with Semantic VAD (Realtime API)
|
|
5
|
424
|
October 1, 2026
|
|
Realtime SIP: accept returns 404 call_id_not_found on every inbound call since 2026-09-10 (worked for months)
|
|
9
|
295
|
October 1, 2026
|
|
REALTIME API BUG - WebSocket stops receiving messages mid-session — AudioWorklet sending audio but no server events fired
|
|
3
|
293
|
September 30, 2026
|
|
Gpt-live-1 responses delegation: voice model sometimes never delegates (acknowledges verbally, sends nothing)
|
|
4
|
345
|
September 30, 2026
|
|
GPT-Live greeting delayed and often glitched (SIP)
|
|
1
|
189
|
September 25, 2026
|
|
Realtime transcription Problem - gpt-live-transcribe - no final events received
|
|
5
|
155
|
September 25, 2026
|
|
Gpt-live-1 switches between masculine and feminine voices mid-call and repeats speech
|
|
0
|
126
|
September 19, 2026
|
|
GPT-Live-1: best voice and prompting for natural French
|
|
3
|
227
|
September 19, 2026
|
|
Gpt-realtime-2.1: production tool invocation regression — model answers instead of calling available tools
|
|
2
|
95
|
September 18, 2026
|
|
GPT Live unavailable in normal chats and silently falls back to WORK/Codex quota
|
|
3
|
267
|
September 17, 2026
|
|
R2Rip: Bringing the personality and continuity of text ChatGPT into a natural voice companion
|
|
0
|
38
|
September 16, 2026
|
|
Can't get the user transcription in realtime api
|
|
10
|
3816
|
September 16, 2026
|
|
Ephemeral keys trigger Realtime sideband 404 errors
|
|
8
|
446
|
September 16, 2026
|
|
Test Webhook often fails on the first attempt
|
|
0
|
28
|
September 15, 2026
|
|
Support for end of turn in gpt-live voice model
|
|
0
|
96
|
September 15, 2026
|
|
Brain context compaction in gpt-live-1
|
|
3
|
270
|
September 14, 2026
|
|
Api-realtime SIP Refer not reaching far end
|
|
2
|
136
|
September 14, 2026
|
|
Gpt-live-1: session.start fails with "Type is not JSON serializable: decimal.Decimal" if any tool schema contains a float
|
|
0
|
77
|
September 14, 2026
|
|
Realtime API: input transcription completion references a nonexistent item after response.cancel and input audio commit
|
|
0
|
49
|
September 13, 2026
|