I picked ElevenLabs bc its the highest quality transcription model I found for my personal use case, but you can use with whatever you want. If you wanna open a pr and implement some open source or other providers, I would for sure merge it :)
Not trying to lock you in, I just wanna make it useful
This is my personal go-to transcriber, and btw it works very well inside Clawdbot/Moltbot
Let me know if you guys like it and/or have any ideas on how can it be improved.