Best speech-to-text and transcription APIs
Transcribe meetings, calls and voice notes. Compare transcription models by live price per unit.
Ordered from lowest price
Live TokenRex prices. Per 1M tokens for chat and embeddings; per unit for media.
| # | Model | Input | Output / unit |
|---|---|---|---|
| 1 | GPT-4o Mini Transcribe gpt-4o-mini-transcribe | — | $0.00302 / per minute |
| 2 | GPT Transcribe gpt-transcribe | — | $0.00458 / per audio minute |
| 3 | Gemini 3.5 Transcribe gemini-3.5-transcribe | — | $0.005 / per minute |
| 4 | GPT-4o Transcribe gpt-4o-transcribe | — | $0.00604 / per minute |
How to choose
- Mini transcription models are good for clear audio; use the full model for noisy recordings.
Try it with one API key
Use the endpoint for the model’s actual type, not Chat Completions. Images, video, speech, embeddings and live audio have different request formats. Open the model page and Docs before submitting your first request.
Head-to-head comparisons
Questions
- How are these transcription models ranked?
- Models are listed from the live TokenRex catalog and ordered by current price. We do not publish invented quality scores; open a model page for source-linked benchmarks where they exist.
- Can I switch models later?
- Yes. Every model uses the same TokenRex API key and endpoint, so switching is a one-line change to the model ID.
- Do prices include a markup?
- Prices shown are the live TokenRex rates billed from your wallet. They update automatically when provider prices change.