Rook Multi Speaker

Speech enhancement for human listening in calls and other real-time audio applications.

Rook Multi Speaker is a production speech-to-speech model by ai-coustics for human-to-human listening β€” conferencing, telephony, and other real-time audio. It perceptually enhances noise, reverb, and distortion at up to 48 kHz β€” 30 ms latency, no GPU needed, no ONNX dependency. Not recommended for Voice AI use cases: use Quail Voice Focus or Quail Multi Speaker there. Inference runs through the aic-sdk Python package (also available for Rust, C/C++, Node.js, and WebAssembly).

Setup

  1. Install the SDK:
    pip install aic-sdk
    
  2. Create a free SDK key on the ai-coustics playground β€” 30-day trial included, no credit card required.

Usage

# initialize the speech enhancement processor
import aic_sdk as aic

model = aic.Model.from_file(aic.Model.download("rook-ms-l-48khz", "./models"))
config = aic.ProcessorConfig.optimal(model)
processor = aic.Processor(model, "{aic-sdk-key}", config)  # get a free SDK key: https://developers.ai-coustics.com/login

# enhance mono float32 audio, one block at a time β€” real-time safe
enhanced_block = processor.process(audio_block)  # shape: (config.block_size,)

Complete example: enhance a WAV file

import wave
import numpy as np
import aic_sdk as aic

license_key = "YOUR_SDK_KEY"  # get a free SDK key: https://developers.ai-coustics.com/login
model = aic.Model.from_file(aic.Model.download("rook-ms-l-48khz", "./models"))

with wave.open("input.wav", "rb") as wf:
    assert wf.getnchannels() == 1, "mono input required"
    sample_rate = wf.getframerate()
    pcm = np.frombuffer(wf.readframes(wf.getnframes()), dtype=np.int16).astype(np.float32) / 32768.0

config = aic.ProcessorConfig.optimal(model, sample_rate=sample_rate)
processor = aic.Processor(model, license_key, config)

enhanced = np.concatenate([
    processor.process(pcm[i : i + config.block_size])
    for i in range(0, len(pcm) - config.block_size + 1, config.block_size)
])

with wave.open("enhanced.wav", "wb") as wf:
    wf.setnchannels(1)
    wf.setsampwidth(2)
    wf.setframerate(sample_rate)
    wf.writeframes((enhanced * 32767).astype(np.int16).tobytes())

Tune the enhancement strength at runtime (useful to optimize for a specific STT engine):

ctx = processor.get_context()
ctx.set_parameter(aic.ProcessorParameter.EnhancementLevel, 0.8)  # 0.0–1.0

Which model should I use?

Family Use it for Notes
Quail Voice Focus Voice agents with one primary speaker Voice isolation: suppresses competing voices and background speech, isolates the foreground speaker. Up to 43% fewer word errors across major STT providers. 16 kHz (usable in 8 kHz pipelines). Supports far-field single-speaker audio. Not suited for multi-speaker scenarios.
Quail Multi Speaker Speech-to-text primer in noisy, far-field, multi-speaker conditions Denoiser optimized for STT accuracy; up to 30% word-error-rate reduction. 8 and 16 kHz.
Rook Multi Speaker Human-to-human listening: conferencing, telephony Perceptual enhancement of noise, reverb, and distortion at up to 48 kHz. Not recommended for Voice AI use cases β€” use Quail there.

Related ai-coustics models

  • πŸ”Š Quail Voice Focus β€” primary-speaker isolation for speech-to-text and voice agents
  • πŸ”Š Quail Multi Speaker β€” multi-speaker speech enhancement for speech-to-text
  • πŸŽ™οΈ VAD Multi Speaker β€” noise-robust VAD for any speaker
  • πŸŽ™οΈ VAD Voice Focus β€” primary-speaker VAD for voice agents
  • πŸ” Tyto β€” predict and diagnose downstream failures in Voice AI stacks

Resources

Downloads last month
26
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support