FluidAudio

FluidAudio is an audio AI library for Apple devices that executes speech-to-text, speaker diarization, voice activity detection, and text-to-speech tasks.

Fluid Inference provides local audio AI capabilities for Apple platforms. It handles speech-to-text transcription, speaker diarization, voice activity detection, and text-to-speech generation. The library executes these models directly on the Apple Neural Engine to ensure local processing. It is designed for developers building applications in Swift. The system requires macOS 14 or iOS 17 and later versions, with Apple Silicon hardware recommended for optimal performance.

FluidAudio at a glance

Best for: Software engineer
Runs on: macOS, iOS
Pricing: Free
Released: June 2025
Category: AI audio tool
Website: docs.fluidinference.com

Key features

Speech-to-text transcription capabilities
Speaker diarization support
Voice activity detection functionality
Text-to-speech generation
On-device model execution via Neural Engine
Native Swift support

Use it for

Transcribing spoken audio into text
Identifying individual speakers in audio recordings
Detecting active speech segments within audio streams
Generating speech from text inputs

Alternatives to FluidAudio

AssemblyAI — Industry-leading speech models deliver high accuracy and low latency for voice applications.
MLX Audio — It enables fast audio model inference directly on Apple M-series chips.
Free ASR — Zero-dependency real-time streaming speech-to-text with no account login required.
audio.cpp — Runs modern audio models locally with high-performance, native C++ execution.
Argmax OSS — Runs AI speech models locally on Apple silicon.
FireRedAudio — A unified model handling understanding and generation with decoupled continuous representations.
Human or AI? — Identifies AI-generated voices in real time directly inside the browser.
Pipecat — Builds real-time voice and multimodal agents with frame-level control.
Piper — Runs locally and offers fast neural text-to-speech synthesis.
talkflow — Transcribes speech entirely on your device with no word limits or cloud accounts
AuK — It handles zero-shot TTS, editing, and enhancement via natural language.
whisper.cpp — It provides high-performance, offline speech recognition on diverse hardware.

All FluidAudio alternatives