Cohere
VoxSynth-2024
audio · Release Jun 1, 2024 · License n/a
A voice synthesis model that generates realistic speech and vocal effects, with customizable tone and emotion settings.
audiosynthesisvoice
Updated today
Modalities
What goes in and what comes out.
Inputs
text
Outputs
audio
Capabilities
voice generation, emotion control, style customization, phoneme accuracy
Benchmarks snapshot
Structured JSON for reproducible comparisons.
{
"realism_score": "4.7/5"
}Related on GenAIWiki
Same provider, tooling that cites the model, or prompts tuned for it.