FluidAudio
No written verdict yet. Here is what commenters said.
Why people recommend it
“Contributing this pipelined setup to FluidAudio would be good.”
“FluidAudio is a big part of this and is actually used in two places during a session.”
Show 3 more
“I'm seeing a lot right here”
“There's a fork of FluidAudio that supports the recent Cohere model”
“Or write your own custom one with the library that backs it”
Caveats and dissent
No one in these comments warned against it.
Often compared with
From the makers not counted in the ranking
Recently contributed a patch to FluidAudio that sped up Parakeet V2 and V3 to 320x and 282x faster than real time, respectively: https://github.com/FluidInference/FluidAudio/pull/507 That means one hour of audio transcribed in 11.25 and 12.75 seconds. The Inscribe post doesn't give a speed factor for SpeechAnalyzer. However, this Argmax blog post reports 70: https://www.argmaxinc.com/blog/apple-and-argmax Based on th
Threads where it came up
- Apple's new SpeechAnalyzer API, benchmarked against Whisper and its predecessor 4 mentions
- item 48521236 3 mentions
- Show HN: Ghost Pepper – 100% local hold-to-talk speech-to-text for macOS 2 mentions
- item 50187193 1 mention
- Ask HN: Got a Mac for running agents? what's your setup? 1 mention
- Show HN: RunAnwhere – Faster AI Inference on Apple Silicon 1 mention
Data: fluidaudio.json. Quotes are verbatim; the verdict and theme labels are written by a model from these comments, and every clause links to its sources.
All comments 14
“I took Hermes, FluidAudio, CUA Driver, WisprKit, and OpenWispr, put it all together”
“runs on-device through FluidAudio's AsrManager, pinned to CPU plus the Neural Engine.”
“Contributing this pipelined setup to FluidAudio would be good.”
“yap/Speechanalyzer is about 50% slower than fluidaudio on M1.”
“I'd like to know how SpeechAnalyzer compares in speed.”
“FluidAudio is a big part of this and is actually used in two places during a session.”
“I'm seeing a lot right here”
“most of these apps are built around”
“There's a fork of FluidAudio that supports the recent Cohere model”
“Or write your own custom one with the library that backs it”
“Other popular repos for such tasks I would recommend:”
“The devs are responsive and active and nice on their discord too.”
“Can use this library”
“Fluid Inference also have great implementations of Parakeet v2/v3 in CoreML for Apple devices”