# speech-to-phrase vs vLLM

> Two self-hosted projects, compared on the numbers selfhost.directory tracks live: score, popularity, release cadence and setup effort.

| | speech-to-phrase | vLLM |
|---|---|---|
| Score | 46/100 | 91/100 ✓ |
| Rank in category | #6 of 11 in Voice Assistants | #3 of 25 in LLM Inference |
| GitHub stars | 348 | 95 811 ✓ |
| Stars, last 30 days | +0 | +3 167 ✓ |
| Stable releases, 12 months | 2 | 14 ✓ |
| Latest release | v1.4.3 · 3 Apr 2026 | v0.32.0 · 17 Oct 2026 ✓ |
| Setup | Advanced | Moderate ✓ |
| Official Docker image | Yes | Yes |
| License | Apache-2.0 | Apache-2.0 |
| Main language | Python | Python |

## Which one should you pick?

vLLM scores 91/100 against 46/100 for speech-to-phrase, so it is the safer default.

vLLM ships more often: 14 stable releases in the past year, against 2 for speech-to-phrase.

If you want the quickest setup, vLLM is easier to run; speech-to-phrase needs more configuration.

vLLM is growing faster right now (+3 167 stars in 30 days).

## Details

- [speech-to-phrase](https://selfhost.directory/project/speech-to-phrase) (markdown: https://selfhost.directory/project/speech-to-phrase.md)
- [vLLM](https://selfhost.directory/project/vllm) (markdown: https://selfhost.directory/project/vllm.md)

---
Source: https://selfhost.directory/compare/speech-to-phrase-vs-vllm