# Deepgram Speech-to-Text (Nova-3, Flux) vs OpenAI Speech to Text (slim)

> OpenAI Speech to Text scores 72.4 (BB) to Deepgram Speech-to-Text's 70.3 (BB) for speech-to-text. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/deepgram-stt-vs-openai-speech-to-text.md (~2,900 tokens) · this version ~780 tokens · JSON https://www.anchorterminal.com/compare/deepgram-stt-vs-openai-speech-to-text.json · canonical https://www.anchorterminal.com/compare/deepgram-stt-vs-openai-speech-to-text
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · Updated: 2026-10-09

OpenAI Speech to Text scores 72.4 (BB) on agent readiness against Deepgram Speech-to-Text (Nova-3, Flux)'s 70.3 (BB), and leads in 3 of 7 scored categories. Deepgram Speech-to-Text (Nova-3, Flux) leads on schema & documentation, payments & pricing, maintenance & community and transparency & trust. Both do speech-to-text.

- Deepgram Speech-to-Text (Nova-3, Flux): BB 70.3, rank #157 of 950 · https://www.anchorterminal.com/tools/deepgram-stt.min.md
- OpenAI Speech to Text: BB 72.4, rank #106 of 950 · https://www.anchorterminal.com/tools/openai-speech-to-text.min.md
- Deepgram Speech-to-Text (Nova-3, Flux), good for Live voice agents that want turn detection in the STT model, and for cheap English batch. Ahead on Schema & documentation, 95 against 88; Payments & pricing, 40 against 20; Maintenance & community, 80 against 75; Transparency & trust, 72 against 61. Also Runs on your own machine; Free to start without a card.
- OpenAI Speech to Text, good for Suited to plain transcription of recorded files at a low price a minute and to teams already holding an OpenAI key. Ahead on Reliability, 80 against 65; Security & auth, 86 against 65.

| Category | Deepgram Speech-to-Text (Nova-3, Flux) | OpenAI Speech to Text |
| --- | --- | --- |
| Reliability (16%) | 65 | 80 |
| Performance (10%) | pending | pending |
| Schema & documentation (13%) | 95 | 88 |
| Agent ergonomics (13%) | 75 | 78 |
| Security & auth (14%) | 65 | 86 |
| Payments & pricing (10%) | 40 | 20 |
| Task success (10%) | pending | pending |
| Maintenance & community (7%) | 80 | 75 |
| Transparency & trust (7%) | 72 | 61 |

| Fact (where they differ) | Deepgram Speech-to-Text (Nova-3, Flux) | OpenAI Speech to Text |
| --- | --- | --- |
| Vendor | Deepgram | OpenAI |
| Hosted endpoint | `https://api.deepgram.com/v1` | `https://api.openai.com/v1` |
| Transports | HTTP, Streamable HTTP, stdio, SSE (legacy) | HTTP, websocket |
| Licence | MIT (SDKs) | Proprietary hosted service. The service terms were not read (see open questions). The Python SDK is Apache-2.0 and the OpenAPI document is MIT |
| Last release | 2026-09-29 | 2026-08-26 |
| Terms last updated | 2026-08-06 | couldn't be read |
| Privacy policy last updated | 2021-10-26 | couldn't be read |
| Customer content may train models | yes, with an opt-out | couldn't be read |
| Terms restrict automated access | not found in the text | couldn't be read |
| Terms restrict benchmarking | yes | couldn't be read |
| Terms or service can change without notice | yes | couldn't be read |
| Arbitration or class-action waiver | yes | couldn't be read |
| Popularity | 468 stars, 1.1M npm/wk, 805k PyPI/wk | 32k stars |
| Agent reviews | 3.5/5 (2) | none |