|
Gpt-4o-mini-transcribe ignores romanization prompts while gpt-4o-transcribe works
|
|
1
|
174
|
July 24, 2025
|
|
Realtime Transcription (speech-to-text) via WebRTC Extremely Delayed – Is This Expected?
|
|
2
|
1068
|
June 10, 2025
|
|
Use new model for realtime audio transcription
|
|
6
|
3885
|
June 5, 2025
|
|
logprobs missing from Realtime Transcription API Responses
|
|
0
|
231
|
June 4, 2025
|
|
Inconsistency in the "Speech to text" documentation
|
|
0
|
122
|
June 2, 2025
|
|
iOS realtime transcribe not working
|
|
0
|
200
|
May 28, 2025
|
|
Whisper ASR Model Skipping Chunks in Audio Transcription
|
|
1
|
920
|
May 20, 2025
|
|
When can we add the SRT return format to gpt-4o-transcribe?
|
|
3
|
1096
|
May 20, 2025
|
|
Realtime transcription api using WebRTC
|
|
0
|
178
|
May 20, 2025
|
|
How to calibrate activation threshold for server VAD?
|
|
0
|
280
|
May 19, 2025
|
|
Transcribing live call (starting stream on Twilio call), after 1-4 min openAI starts to degrade
|
|
0
|
150
|
May 16, 2025
|
|
On message type "conversation.item.input_audio_transcription.completed" returns prompt
|
|
0
|
101
|
May 16, 2025
|
|
OpenAI 40 mini transcription realtime isn't working since yesterday, error is 400 and it says that reatime api isn't available, anyclue?
|
|
2
|
240
|
May 4, 2025
|
|
Gpt 4o - Transcribe is not providing results in a single language
|
|
1
|
367
|
April 25, 2025
|
|
Unknown parameter: 'modalities'. when creating transcriptionSessions
|
|
5
|
463
|
April 25, 2025
|
|
Random response from new transcribe models
|
|
0
|
236
|
April 22, 2025
|
|
ERR_NETWORK when calling /v1/audio/transcriptions API
|
|
3
|
455
|
April 22, 2025
|
|
`gpt-4o-transcribe` drops the end of recordings
|
|
1
|
377
|
April 20, 2025
|
|
4o-mini-transcribe not respecting language option
|
|
0
|
316
|
April 19, 2025
|
|
Invalid 'input_audio_transcription.prompt': string too long
|
|
3
|
325
|
April 11, 2025
|
|
Realtime/transcription_sessions API returns 401 even when adding ephemeral key
|
|
8
|
752
|
April 7, 2025
|
|
Streaming Response Delay in GPT-4o Transcribe: Issue with Real-Time Audio Chunking
|
|
0
|
267
|
April 1, 2025
|
|
Reproducing gpt-4o-transcribe FLEURS results
|
|
5
|
568
|
April 1, 2025
|
|
Gpt-4o-transcribe unsupported format with .wav
|
|
2
|
1380
|
March 27, 2025
|
|
Transcriptions API disable auto grammar correction
|
|
0
|
147
|
January 21, 2025
|
|
TTS and SST for multilingual audio
|
|
0
|
383
|
October 9, 2024
|
|
High error rate for Whisper transcriptions API
|
|
0
|
229
|
July 14, 2024
|
|
Transcriptions API calls failing with socket hang up
|
|
5
|
1528
|
April 28, 2024
|
|
Problems with Audio-to-Text Transcription Using PHP: Issues Sending File Path to OpenAI API
|
|
0
|
550
|
May 15, 2024
|
|
A crazy idea or it's feasible: Technique that saves 30% on Transcribe Costs
|
|
32
|
4144
|
May 5, 2024
|