Help required with Mimic3 Python implementation

Speech and Generative AI Text To Speech (TTS / NLG)
1

Hi All,
I am new to Mimic3 here and want to implement TTS feature in python. Mimic3 sound promising to me apart from other opensource TTS engines. Please guide me through the python api.
What I am trying to achieve is:

Synthesize it in a voice ==== Stuck with Mimic3 implementation (maybe .speak_text() is doing it’s job but I am not aware)
Play the voice ----- need to be done directly from python sounddevice.play() or something like that.

This is what I have tried so far…

from mimic3_tts import AudioResult, Mimic3Settings,Mimic3TextToSpeechSystem

s = Mimic3Settings()
s.language=“en_US”
s.voice = “en_US/cmu-arctic_low”
s.volume=50.0
#s.voices_directories = “/home/mimicvoices/”

m = Mimic3TextToSpeechSystem(s)

m.begin_utterance()
print(m.speak_text(“Hello World!!!”))
m.end_utterance()

print(“done”)

Also it is worth noting that every time I run the mimic3 (let it be from terminal or python) it starts downloading few files and takes ages to complete. I know I am missing something here otherwise this shouldn’t be the case.

2

When MycroftAI wound down, the Mimic3 developer went here:

This is what the surviving Assistant projects recommend instead. Mimic is effectively abandonware.

2 Likes
3

Thanks a lot. That help me a lot