Azure AI Speech needs seconds of audio to clone voices
SMRTR summary
Microsoft's upgraded Azure AI Speech now creates accurate voice replicas with minimal audio input. The "DragonV2.1Neural" model offers natural-sounding voices in over 100 languages, enhancing prosody and pronunciation. While enabling innovative applications, this technology raises concerns about potential misuse. Microsoft has implemented safeguards, including watermarks and consent policies, but AI voice cloning advancements continue to outpace protective measures.
SMRTR provides this summary for quick context. The original article belongs to Daily.dev.
Read the original article