# llama.cpp vs speech-to-phrase

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

| | llama.cpp | speech-to-phrase |
|---|---|---|
| Score | 93/100 ✓ | 46/100 |
| Rank in category | #2 of 25 in LLM Inference | #6 of 11 in Voice Assistants |
| GitHub stars | 132 689 ✓ | 348 |
| Stars, last 30 days | +3 234 ✓ | +0 |
| Stable releases, 12 months | 1463 ✓ | 2 |
| Latest release | b11977 · 29 Oct 2026 ✓ | v1.4.3 · 3 Apr 2026 |
| Setup | Moderate ✓ | Advanced |
| Official Docker image | Yes | Yes |
| License | MIT | Apache-2.0 |
| Main language | C++ | Python |

## Which one should you pick?

llama.cpp scores 93/100 against 46/100 for speech-to-phrase, so it is the safer default.

llama.cpp ships more often: 1463 stable releases in the past year, against 2 for speech-to-phrase.

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

llama.cpp is growing faster right now (+3 234 stars in 30 days).

## Details

- [llama.cpp](https://selfhost.directory/project/llamacpp) (markdown: https://selfhost.directory/project/llamacpp.md)
- [speech-to-phrase](https://selfhost.directory/project/speech-to-phrase) (markdown: https://selfhost.directory/project/speech-to-phrase.md)

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