|
Simple hack to make LLMs listen to an audio rather than only reading
|
|
1
|
110
|
November 12, 2025
|
|
Chat completions audio output but not base64 encoded string
|
|
5
|
266
|
October 10, 2025
|
|
Realtime Transcription (speech-to-text) via WebRTC Extremely Delayed – Is This Expected?
|
|
2
|
817
|
June 10, 2025
|
|
Any idea why text-to-speech hallucinate when using phonetic symbols
|
|
1
|
139
|
June 3, 2025
|
|
How to use text to speech api to stream realtime audio with nodejs?
|
|
0
|
128
|
March 24, 2025
|
|
An idea for Android app developers
|
|
9
|
999
|
December 21, 2024
|
|
Is it possible to specify output language in text-to-speech?
|
|
2
|
303
|
December 2, 2024
|
|
Whipser-1 skip a big chunk of audio when transcribing
|
|
0
|
98
|
September 3, 2024
|
|
ChatGPT Completion speech to text is no longer working
|
|
1
|
355
|
August 13, 2024
|
|
Speech to Speech via API vs. waiting for GPT-4o voice
|
|
2
|
388
|
August 9, 2024
|
|
Generating single words in the Text-to-Speech API
|
|
0
|
204
|
July 18, 2024
|
|
TTS: add emphasis to one word in spoken text
|
|
11
|
2710
|
June 30, 2024
|
|
Voice and audio - gpt-4o - any updates?
|
|
0
|
1856
|
June 7, 2024
|
|
A crazy idea or it's feasible: Technique that saves 30% on Transcribe Costs
|
|
32
|
3580
|
May 5, 2024
|