tts output on sytellite sluggish

[Rihan9]

Hi,
I'm using a raspberry pi 4 with 2GB of ram, and a wired connection with a performance of 930Mbps misured with iperf3. (300Mbps with the External).
I shouldn't have any performance issue, but the wyoming satellite voice aoutput is sluggish and unsettling. It seems like it's played at 0.70x speed.

If I use Home Assistant Assist directly from the browser, this problem doesn't exist. What can I do? I even tried to use the standard headphones jack on the raspberry and I'm currently using it.

/wyoming-satellite/script/run
    --name 'satellite'
    --uri 'tcp://0.0.0.0:10700'
    --mic-command 'arecord -D plughw:CARD=seeed2micvoicec,DEV=0 -r 16000 -c 1 -f S16_LE -t raw'
    --snd-command 'aplay -D plughw:CARD=Headphones,DEV=0 -r 16000 -c 1 -f S16_LE -t raw'
    --wake-uri 'tcp://127.0.0.1:10400'
    -wake-word-name 'ok_nabu'
    --event-uri 'tcp://127.0.0.1:10500'

What am I doing wrong? a wav clip played with:

aplay -D plughw:CARD=Headphones,DEV=0 -r 16000 -c 1 -f S16_LE ./test.wav

doesn't have the same issue.