mirror of
https://github.com/memohai/Memoh.git
synced 2026-04-27 07:16:19 +09:00
Acbox
925fdee478
* feat: expand speech provider support with new client types and configuration schema * feat: add icon support for speech providers and update related configurations * feat: add SVG support for Deepgram and Elevenlabs with Vue components * feat: except *-speech client type in llm provider * feat: enhance speech provider functionality with advanced settings and model import capabilities * chore: remove go.mod replace * feat: enhance speech provider functionality with advanced settings and model import capabilities * chore: update go module dependencies * feat: Ear and Mouth * fix: separate ear/mouth page * fix: separate audio domain and restore transcription templates Move speech and transcription internals into the audio domain, restore template-driven transcription providers, and regenerate Swagger/SDK so the frontend can stop hand-calling /transcription-* APIs. --------- Co-authored-by: aki <arisu@ieee.org>
21 lines
468 B
Go
21 lines
468 B
Go
package audio
|
|
|
|
import "context"
|
|
|
|
type TtsType string
|
|
|
|
type TtsMeta struct {
|
|
Provider string
|
|
Description string
|
|
}
|
|
|
|
type TtsAdapter interface {
|
|
Type() TtsType
|
|
Meta() TtsMeta
|
|
DefaultModel() string
|
|
Models() []ModelInfo
|
|
ResolveModel(model string) (string, error)
|
|
Synthesize(ctx context.Context, text string, model string, config AudioConfig) ([]byte, error)
|
|
Stream(ctx context.Context, text string, model string, config AudioConfig) (chan []byte, chan error)
|
|
}
|