Fish SpeechvsLLM Vision
Two self-hosted projects, compared on the numbers selfhost.directory tracks live: score, popularity, release cadence and setup effort.
| Fish Speech | LLM Vision | |
|---|---|---|
| Score | 73/100 | 63/100 |
| Rank in category | #3 of 9 in Text to Speech | #19 of 104 in Home Automation |
| GitHub stars | 33 454 | 1 518 |
| Stars, last 30 days | +131 | +41 |
| Stable releases, 12 months | 0 | 4 |
| Latest release | — | v1.7.2 · 3 Sept 2026 |
| Setup | Advanced | Moderate |
| Official Docker image | Yes | No |
| License | Other | Apache-2.0 |
| Main language | Python | Python |
Which one should you pick?
Fish Speech scores 73/100 against 63/100 for LLM Vision, so it is the safer default.
LLM Vision ships more often: 4 stable releases in the past year, against 0 for Fish Speech.
If you want the quickest setup, LLM Vision is easier to run; Fish Speech needs more configuration.
Fish Speech is growing faster right now (+131 stars in 30 days).
Fish Speech details →LLM Vision details →
Swap a project
Keep Fish Speech, compare it with
Keep LLM Vision, compare it with