TTS API improvements (#2308)

* update doc on COQUI_LANGUAGE env variable

Signed-off-by: blob42 <contact@blob42.xyz>

* return errors from tts gRPC backend

Signed-off-by: blob42 <contact@blob42.xyz>

* handle speaker_id and language in coqui TTS backend

Signed-off-by: blob42 <contact@blob42.xyz>

* TTS endpoint: add optional language paramter

Signed-off-by: blob42 <contact@blob42.xyz>

* tts fix: empty language string breaks non-multilingual models

Signed-off-by: blob42 <contact@blob42.xyz>

* allow tts param definition in config file

- consolidate TTS options under `tts` config entry

Signed-off-by: blob42 <contact@blob42.xyz>

* tts: update doc

Signed-off-by: blob42 <contact@blob42.xyz>

---------

Signed-off-by: blob42 <contact@blob42.xyz>
Co-authored-by: Ettore Di Giacinto <mudler@users.noreply.github.com>

core/config/backend_config.go

@@ -15,6 +15,15 @@ const (
 	RAND_SEED = -1
 )
 
+type TTSConfig struct {
+
+	// Voice wav path or id
+	Voice string `yaml:"voice"`
+
+	// Vall-e-x
+	VallE    VallE  `yaml:"vall-e"`
+}
+
 type BackendConfig struct {
 	schema.PredictionOptions `yaml:"parameters"`
 	Name                     string `yaml:"name"`
@@ -49,8 +58,8 @@ type BackendConfig struct {
 	// GRPC Options
 	GRPC GRPC `yaml:"grpc"`
 
-	// Vall-e-x
-	VallE VallE `yaml:"vall-e"`
+	// TTS specifics
+	TTSConfig `yaml:"tts"`
 
 	// CUDA
 	// Explicitly enable CUDA or not (some backends might need it)