F5-TTS
JSON →A flow-matching text-to-speech model by SWivid offering high-quality voice synthesis with natural expressiveness.
Capabilities
streaming
Dates
releasedOct 2024
API
full doc /v1/models/SWivid/F5-TTS
A flow-matching text-to-speech model by SWivid offering high-quality voice synthesis with natural expressiveness.