GENAIWIKI

Meta

Meta-VoiceSynth-2023

audio · Release Jul 25, 2023 · License n/a

A neural voice synthesis model capable of producing realistic human speech with emotional intonations.

voice synthesisTTSaudio
Updated today

Modalities

What goes in and what comes out.

Inputs

text

Outputs

audio

Capabilities

text-to-speech, voice customization, emotion synthesis, multi-language support

Benchmarks snapshot

Structured JSON for reproducible comparisons.

{
  "naturalness_score": 9.5
}

Related on GenAIWiki

Same provider, tooling that cites the model, or prompts tuned for it.