Introducing next-generation audio models in the API
https://openai.com/index/introducing-our-next-generation-audio-models/
Speech-to-text
gpt-4o-transcribe
gpt-4o-mini-transcribe
OpenAI Whisper
を超えたclosedモデル
text-to-speech
gpt-4o-mini-tts
OpenAI.fm
IMO：
Sesami
や
Moshi
と比べてどうなんだろう？
examples
https://github.com/openai/openai-agents-python/tree/main/examples/voice
#openai-agents
VoicePipeline（TODO：積ん読）
https://x.com/OpenAIDevs/status/1902817202358685880
https://www.youtube.com/live/lXb0L16ISAc?si=GD3l6tAQU-opJOEJ