Could OpenAI add a audio_length or words_per_second parameter to TTS?
A fixed rate would allow precise, consistent audio length across voices and texts, ideal for syncing with visuals or subtitles.
Example:
"audio_length": 12.8
Thanks!
Could OpenAI add a audio_length or words_per_second parameter to TTS?
A fixed rate would allow precise, consistent audio length across voices and texts, ideal for syncing with visuals or subtitles.
Example:
"audio_length": 12.8
Thanks!
Welcome to the community @KarimB!
Changed this to the API > Feedback category for you.
OpenAI team members are known to browse and occasionally post here.
Hope you stick around. We’ve got a great bunch of people and a wealth of knowledge here.