FluidInference FluidAudio by FluidInference

Frontier CoreML audio models in your apps, text-to-speech, speech-to-text, voice activity detection, and speaker diarization. In Swift, powered by SOTA open source.

coremliosmacosspeaker-diarizationspeaker-embeddingspeaker-identificationspeaker-recognitionswiftaudioavfoundationreal-timevad
Verdict 70/100 health $4.13/mo cheapest, hetzner 2/5 setup difficulty Last release 3 days ago

Self-host FluidInference FluidAudio on hetzner CAX11 for $4.13/mo.

Health score
70 /100
6-dim composite
Self-hosts from
$4.13 /mo
hetzner · CAX11
Difficulty
2 /5
Docker + read README
GitHub stars
2.0k
270 forks

About FluidInference FluidAudio

From the project's README at github.com/FluidInference/FluidAudio. Lightly cleaned for readability; for the full source see the upstream repo.

[](https://swift.org) [](https://developer.apple.com) [](https://docs.fluidinference.com/introduction) [](https://discord.gg/WNsvaCtmDe) [](https://huggingface.co/FluidInference) [](https://deepwiki.com/FluidInference/FluidAudio)

FluidAudio is a Swift SDK for fully local, low-latency audio AI on Apple devices, with inference offloaded to the Apple Neural Engine (ANE), resulting in less memory and generally faster inference.

The SDK includes state-of-the-art speaker diarization, transcription, and voice activity detection via open-source models (MIT/Apache 2.0) that can be integrated with just a few lines of code. Models are optimized for background processing, ambient computing and always on workloads by running inference on the ANE, minimizing CPU usage and avoiding GPU/MPS entirely.

For custom use cases, feedback, additional model support, or platform requests, join our [Discord](https://d

Health score breakdown

6-dimension composite. See methodology for formula and weights.

activity
93
maturity
77
community
92
security
70
sustainability
53
adoption
30

Adoption signals

Real-world usage data, pulled from each registry. The bigger the numbers, the more battle-tested the project.

SignalValueSource
GitHub stars 2.0k github.com/FluidInference/FluidAudio
GitHub forks 270 github.com/FluidInference/FluidAudio

Release & maintenance

Is this project actively maintained, or about to die? Check the recency of last commit and last release.

Project age0.9 yearssince Jun 2025
Last commit2 days agoMay 5, 2026
Releases shipped54last: 3 days ago

Self-hosting cost across providers

Detected requirements: 4GB RAM, 40GB disk minimum. Cheapest plan per provider that meets the requirement.

ProviderPlanSpecsMonthly
hetzner CAX11 2c · 4GB · 40GB $4.13 USD Deploy →
vultr VC2 1c · 1GB · 25GB $5 USD Deploy →
linode Nanode 1GB 1c · 1GB · 25GB $5.12 USD Deploy →
digitalocean Basic Regular 1GB 1c · 1GB · 25GB $6 USD Deploy →

What people say on Hacker News

Ready to self-host FluidInference FluidAudio?

Spin up a hetzner CAX11 (4GB RAM, 40GB disk) for $4.13/mo and follow the project's official install docs.

Data last refreshed May 7, 2026.

Similar open-source projects

Projects in our directory that replace the same SaaS or share topics with FluidInference FluidAudio.

Frequently asked questions

Last verified . Data refreshes every 30 minutes.