Does 'eleven_multilingual_v2' supports long texts?

[devbusca]

Happens when I try to convert text in Spanish to audio, it has many failures, for example the voice audio is gradually decreasing. Other times it speaks as if it had the voice in another language, but it tries to speak Spanish and it sounds quite bad. Also with Roman numerals, sometimes says them, sometimes doesn't, it's a bit random.

[devbusca]

And how can i change stability if im using this way the API?

` audio = generate( text=text, api_key=elevenlabs_key, voice= 'Josh', model=language

"eleven_multilingual_v2"

    # "eleven_monolingual_v1"
)
save(audio, filepath)`

[flavioschneider]

Changing the voice settings might help, here's an example on how to do that (after v0.2.25)

from elevenlabs import Voice, VoiceSettings, generate

audio = generate(
    text="Hello! My name is Bella.",
    voice=Voice(
        voice_id='EXAVITQu4vr4xnSDxMaL',
        settings=VoiceSettings(stability=0.71, similarity_boost=0.5, style=0.0, use_speaker_boost=True)
    )
)

play(audio)