Speech-to-text and transcription models
Speech-to-text is the first step in many voice pipelines: meetings, call centers, captions. Today the public catalog highlights Whisper-1; the same Geek Hub key works for STT and for the LLM that summarizes after.
Models in this collection
| Model | Type | Context | Price |
|---|---|---|---|
 OpenAI Whisper-1OpenAI | STT | — | $0.0065 / min |
Why these models
Whisper-1 is the OpenAI-compatible transcription workhorse: solid across languages and easy to chain with a chat model from another collection.
Use them with Geek Hub
One OpenAI-compatible base URL and API key. Swap any model id from this list without rewriting your client.
Get an API keyFAQ
- Only one STT model?
- In this curated page yes (Whisper-1). The gateway may add providers; this collection updates when more public ids ship.
- How is it billed?
- Per minute of audio. See the table for price.
- Typical pipeline?
- Audio → Whisper → chat (Flash/mini) for summary or CRM. Same API key.