Public KG record
Voice Design
Recorded overview
Generates new voices from text descriptions via prompt expansion; requires no re
An evidence-backed entity from the project knowledge graph; detailed tool metadata is still being added.
Recorded details
- Benchmarks: InstructTTSEval
- Capabilities: generates new voices from text descriptions
- Deployment: API and Studio
- Deployment: Gradium API and Studio
- Languages: English, French, Spanish, Portuguese, German
- Supported types: text-to-speech
- Supported types: input: 1 to 500 characters of text
- Supported types: output: synthetic voice audio
Evidence coverage
The KG currently records 11 known information dimensions and has 7 undocumented dimensions, linked to 1 public source articles. These counts describe record coverage, not model performance or verified fit.
Related public records
- ElevenLabs — competes with
- Fish Audio — competes with
- Gradium AI — releases
- Inworld — competes with
- MiniMax — competes with