What is Whisper (transcription)?
Whisper (transcription) is a ai & search tool. With OSP.net, your AI agent connects to it directly so it can act on your behalf instead of just answering questions about it.
What your OSP agent can do with Whisper (transcription)
- Transcribe video audio in the Video Watch skill
- Works with a Groq key (fast, free tier) or an OpenAI key
How to connect Whisper (transcription)
- Easiest: get a free Groq key — sign in at Groq Console, open API Keys, create one (gsk_…). Groq hosts Whisper with a generous free tier. console.groq.com → API Keys
- Or use OpenAI: create a key at the OpenAI dashboard (sk-…). Whisper transcription is pay-as-you-go there. platform.openai.com → API keys
- Paste either key here and Connect. The Video Watch skill picks it up automatically the next time your agent runs it.
Security: This key is used only to transcribe video audio in the Video Watch skill. Rotate it any time from your Groq or OpenAI dashboard.
Who uses Whisper (transcription) with OSP
These roles commonly connect Whisper (transcription) to their OSP agent:
Related ai & search integrations
Frequently asked questions
- Can OSP.net connect to Whisper (transcription)?
- Yes. Whisper (transcription) is a native OSP.net integration — you bring your own Whisper (transcription) key or token, paste it in your dashboard, and your agent restarts live.
- What can my OSP agent do with Whisper (transcription)?
- Powers transcription for the Video Watch skill — paste a Groq or OpenAI key and your agent can read what's said in a video. Specifically: Transcribe video audio in the Video Watch skill; Works with a Groq key (fast, free tier) or an OpenAI key.
- Is Whisper (transcription) a native integration or via the gateway?
- Whisper (transcription) is a native, baked-in integration. You connect it with your own credentials, which are stored in an encrypted vault and injected only at runtime.
- Is my Whisper (transcription) data secure with OSP.net?
- Yes. Your Whisper (transcription) credentials live in an encrypted secrets vault, are injected only at container runtime, and are never written to disk in plaintext or used to train any model. Each customer runs in a fully isolated instance.