Merge branch 'master' of github.com:taigrr/elevenlabs

This commit is contained in:
2023-06-26 20:09:02 -07:00
4 changed files with 30 additions and 4 deletions

View File

@@ -13,11 +13,12 @@ import (
"github.com/taigrr/elevenlabs/client/types"
)
func (c Client) TTSWriter(ctx context.Context, w io.Writer, text, voiceID string, options types.SynthesisOptions) error {
func (c Client) TTSWriter(ctx context.Context, w io.Writer, text, modelID, voiceID string, options types.SynthesisOptions) error {
options.Clamp()
url := fmt.Sprintf(c.endpoint+"/v1/text-to-speech/%s", voiceID)
opts := types.TTS{
Text: text,
ModelID: modelID,
VoiceSettings: options,
}
b, _ := json.Marshal(opts)
@@ -55,12 +56,13 @@ func (c Client) TTSWriter(ctx context.Context, w io.Writer, text, voiceID string
}
}
func (c Client) TTS(ctx context.Context, text, voiceID string, options types.SynthesisOptions) ([]byte, error) {
func (c Client) TTS(ctx context.Context, text, voiceID, modelID string, options types.SynthesisOptions) ([]byte, error) {
options.Clamp()
url := fmt.Sprintf(c.endpoint+"/v1/text-to-speech/%s", voiceID)
client := &http.Client{}
opts := types.TTS{
Text: text,
ModelID: modelID,
VoiceSettings: options,
}
b, _ := json.Marshal(opts)

View File

@@ -19,6 +19,7 @@ type Voice struct {
Labels string `json:"labels,omitempty"` // Serialized labels dictionary for the voice.
}
type TTS struct {
ModelID string `json:"model_id"`
Text string `json:"text"` // The text that will get converted into speech. Currently only English text is supported.
VoiceSettings SynthesisOptions `json:"voice_settings,omitempty"` // Voice settings are applied only on the given TTS request.
}
@@ -103,6 +104,22 @@ type LanguageResponseModel struct {
IsoCode string `json:"iso_code"`
DisplayName string `json:"display_name"`
}
type Language struct {
LanguageID string `json:"language_id"`
Name string `json:"name"`
}
type ModelResponseModel struct {
ModelID string `json:"model_id"`
Name string `json:"name"`
Description string `json:"description"`
CanBeFinetuned bool `json:"can_be_finetuned"`
CanDoTextToSpeech bool `json:"can_do_text_to_speech"`
CanDoVoiceConversion bool `json:"can_do_voice_conversion"`
TokenCostFactor float64 `json:"token_cost_factor"`
Languages []Language `json:"languages"`
}
type RecordingResponseModel struct {
RecordingID string `json:"recording_id"`
MimeType string `json:"mime_type"`