Documentation
¶
Overview ¶
Package xtts provides text-to-speech via a self-hosted Coqui XTTS streaming server (https://github.com/coqui-ai/xtts-streaming-server). The server holds the voices; this client fetches a studio speaker's embeddings once and streams raw 24 kHz PCM for each sentence.
Index ¶
Constants ¶
This section is empty.
Variables ¶
This section is empty.
Functions ¶
Types ¶
type Config ¶
type Config struct {
// BaseURL is the XTTS streaming server base (e.g. http://localhost:8000). Required.
BaseURL string `validate:"required"`
// Voice is the studio speaker name to synthesize with. Required.
Voice string `validate:"required"`
// Language is the synthesis language code; empty uses "en".
Language string
// SampleRate is the PCM output rate reported downstream; 0 uses 24 kHz.
SampleRate int
}
Config configures a Coqui XTTS streaming-server TTS service.
Source Files
Click to show internal directories.
Click to hide internal directories.