Computational Model Studio · Model release
Kokoro v1.0
Turns supplied text into synthesized speech using a downloadable v1.0 checkpoint.
Developer: hexgrad · Last verified:
What it is designed to do
Generate spoken audio from text with a selected supported voice.
Documented uses: Producing spoken audio from text using documented voice choices.
Access and deployment
- Kokoro v1.0 model files — available. Public publisher repository; review applicable terms before use. Artifact documentation Local hardware requirements have not been verified. The full artifact-specific rights document has not been separately reviewed; consult the publisher repository conditions.
Technical profile and review notes
- Construction
- learned
- Representation
- neural
- Normalized architecture tags
- No normalized architecture tag assigned
- Lifecycle
- Unknown from reviewed sources
Inclusion rationale: Adds audio output and a speech-generation function distinct from transcription and text generation.
Limitations
- Voice and language support are checkpoint-scoped; small model size alone is not evidence of laptop or mobile feasibility.
Sources and related Studio records
Sources
Connections
- In areaComputational Models
- Supports functionSynthesize speech
- ArtifactKokoro v1.0 model files