Question about quality of voice
thevickypedia opened this issue · comments
Hello,
I'm looking for some clarification towards getting a text converted to speech in low quality. I run larynx
in a docker container and use python's requests
module to make a post
call to the endpoint 0.0.0.0:5002/api/tts
to get the audio output.
requests.post(
url="http://0.0.0.0:5002/api/tts", params={"voice": "en-us_northern_english_male-glow_tts"},
data='Welcome to the world of speech synthesis!', headers={"Content-Type": "text/plain"}, verify=False
)
I tried adding 'quality': 'low'
as part of the params
but it keeps defaulting to VocoderQuality.HIGH
Your readme says,
You can specify the vocoder quality by adding ; to the MaryTTS voice where QUALITY is "high", "medium", or "low".
I naively tried using params={"voice": "en-us_northern_english_male-glow_tts;low"}
but ended up getting the following error since the source URL is malformed by it,
ERROR:larynx:Failed to download voice en-us_northern_english_male-glow_tts;low from http://github.com/rhasspy/larynx/releases/download/v1.0/en-us_northern_english_male-glow_tts;low.tar.gz: HTTP Error 404: Not Found
Any clarity on this would be much helpful. Thank you.
After looking into the docker logs, I figured it is simply vcoder
param
requests.post(
url="http://0.0.0.0:5002/api/tts", params={"voice": "en-us_northern_english_male-glow_tts", "vocoder": "low"},
data='Welcome to the world of speech synthesis!', headers={"Content-Type": "text/plain"}, verify=False
)
Hence, closing the issue.