Reintroduce TTS WS

deepgram · Jul 15, 2024 · d11c946 · d11c946
1 parent 8287a80
commit d11c946
Show file tree

Hide file tree

Showing 14 changed files with 1,784 additions and 68 deletions.
diff --git a/README.md b/README.md
@@ -39,6 +39,11 @@ For documentation relating to Speech-to-Text (and Intelligence) from PreRecorded
 
 For documentation relating to Text-to-Speech:
 
+- WebSocket:
+  - Speak REST Client - [https://pkg.go.dev/github.com/deepgram/deepgram-go-sdk@main/pkg/client/speak/v1/websocket](https://pkg.go.dev/github.com/deepgram/deepgram-go-sdk@main/pkg/client/speak/v1/websocket)
+  - Speak REST API - [https://pkg.go.dev/github.com/deepgram/deepgram-go-sdk@main/pkg/api/speak/v1/websocket](https://pkg.go.dev/github.com/deepgram/deepgram-go-sdk@main/pkg/api/speak/v1/websocket)
+  - Speak API Interfaces - [https://pkg.go.dev/github.com/deepgram/deepgram-go-sdk@main/pkg/api/speak/v1/websocket/interfaces](https://pkg.go.dev/github.com/deepgram/deepgram-go-sdk@main/pkg/api/speak/v1/websocket/interfaces)
+
 - REST:
   - Speak REST Client - [https://pkg.go.dev/github.com/deepgram/deepgram-go-sdk@main/pkg/client/speak/v1/rest](https://pkg.go.dev/github.com/deepgram/deepgram-go-sdk@main/pkg/client/speak/v1/rest)
   - Speak REST API - [https://pkg.go.dev/github.com/deepgram/deepgram-go-sdk@main/pkg/api/speak/v1/rest](https://pkg.go.dev/github.com/deepgram/deepgram-go-sdk@main/pkg/api/speak/v1/rest)
@@ -153,6 +158,11 @@ Speech-to-Text - Live Audio:
 - From a Microphone - [examples/speech-to-text/websocket/microphone](https://github.com/deepgram/deepgram-go-sdk/blob/main/examples/speech-to-text/websocket/microphone/main.go)
 - From an HTTP Endpoint - [examples/speech-to-text/websocket/http](https://github.com/deepgram/deepgram-go-sdk/blob/main/examples/speech-to-text/websocket/http/main.go)
 
+Text-to-Speech - WebSocket
+
+- Websocket Simple Example - [examples/text-to-speech/websocket/simple](https://github.com/deepgram/deepgram-go-sdk/blob/main/examples/text-to-speech/websocket/simple/main.go)
+- Interactive Websocket - [examples/text-to-speech/websocket/interactive](https://github.com/deepgram/deepgram-go-sdk/blob/main/examples/text-to-speech/websocket/interactive/main.go)
+
 Text-to-Speech - REST
 
 - Save audio to a Path - [examples/text-to-speech/rest/file](https://github.com/deepgram/deepgram-go-sdk/blob/main/examples/text-to-speech/rest/file/main.go)

diff --git a/docs.go b/docs.go
@@ -30,5 +30,5 @@ import (
 	_ "github.com/deepgram/deepgram-go-sdk/pkg/api/listen/v1/websocket"
 	_ "github.com/deepgram/deepgram-go-sdk/pkg/api/manage/v1"
 	_ "github.com/deepgram/deepgram-go-sdk/pkg/api/speak/v1/rest"
-	// _ "github.com/deepgram/deepgram-go-sdk/pkg/api/speak/v1/websocket"
+	_ "github.com/deepgram/deepgram-go-sdk/pkg/api/speak/v1/websocket"
 )
diff --git a/examples/text-to-speech/websocket/interactive/main.go b/examples/text-to-speech/websocket/interactive/main.go
@@ -0,0 +1,159 @@
+// Copyright 2024 Deepgram SDK contributors. All Rights Reserved.
+// Use of this source code is governed by a MIT license that can be found in the LICENSE file.
+// SPDX-License-Identifier: MIT
+
+package main
+
+import (
+	"bufio"
+	"context"
+	"fmt"
+	"os"
+	"strings"
+	"time"
+
+	msginterfaces "github.com/deepgram/deepgram-go-sdk/pkg/api/speak/v1/websocket/interfaces"
+	interfaces "github.com/deepgram/deepgram-go-sdk/pkg/client/interfaces"
+	speak "github.com/deepgram/deepgram-go-sdk/pkg/client/speak"
+)
+
+const (
+	API_KEY    = ""
+	TTS_TEXT   = "Hello, this is a text to speech example using Deepgram."
+	AUDIO_FILE = "output.mp3"
+)
+
+// Implement your own callback
+type MyCallback struct{}
+
+func (c MyCallback) Metadata(md *msginterfaces.MetadataResponse) error {
+	fmt.Printf("\n[Metadata] Received\n")
+	fmt.Printf("Metadata.RequestID: %s\n", strings.TrimSpace(md.RequestID))
+	return nil
+}
+
+func (c MyCallback) Binary(byMsg []byte) error {
+	fmt.Printf("\n[Binary] Received\n")
+
+	file, err := os.OpenFile(AUDIO_FILE, os.O_CREATE|os.O_WRONLY|os.O_TRUNC, 0o666)
+	if err != nil {
+		fmt.Printf("Error creating file %s: %v\n", AUDIO_FILE, err)
+		return err
+	}
+	defer file.Close()
+
+	_, err = file.Write(byMsg)
+	if err != nil {
+		fmt.Printf("Error writing audio data to file: %v\n", err)
+		return err
+	}
+
+	fmt.Printf("Audio data saved to %s\n", AUDIO_FILE)
+	return nil
+}
+
+func (c MyCallback) Flush(fl *msginterfaces.FlushedResponse) error {
+	fmt.Printf("\n[Flushed] Received\n")
+	fmt.Printf("\n\nPress 'r' and ENTER to reset the buffer, 'f' and ENTER to flush, enter new text to send it, or just ENTER to exit...\n\n> ")
+	return nil
+}
+
+func (c MyCallback) Warning(wr *msginterfaces.WarningResponse) error {
+	fmt.Printf("\n[Warning] Received\n")
+	fmt.Printf("Warning.Code: %s\n", wr.WarnCode)
+	fmt.Printf("Warning.Description: %s\n\n", wr.WarnMsg)
+	return nil
+}
+
+func (c MyCallback) Error(er *msginterfaces.ErrorResponse) error {
+	fmt.Printf("\n[Error] Received\n")
+	fmt.Printf("Error.Code: %s\n", er.ErrCode)
+	fmt.Printf("Error.Description: %s\n\n", er.Description)
+	return nil
+}
+
+func (c MyCallback) Close(cr *msginterfaces.CloseResponse) error {
+	fmt.Printf("\n[Close] Received\n")
+	return nil
+}
+
+func (c MyCallback) Open(or *msginterfaces.OpenResponse) error {
+	fmt.Printf("\n[Open] Received\n")
+	return nil
+}
+
+func main() {
+	// init library
+	speak.InitWithDefault()
+
+	// Go context
+	ctx := context.Background()
+
+	// print instructions
+	fmt.Print("\n\nPress ENTER to exit!\n\n")
+
+	// set the TTS options
+	ttsOptions := &interfaces.SpeakOptions{
+		Model: "aura-asteria-en",
+	}
+
+	// set the Client options
+	cOptions := &interfaces.ClientOptions{}
+
+	// create the callback
+	callback := MyCallback{}
+
+	// create a new stream using the NewStream function
+	dgClient, err := speak.NewWebSocket(ctx, "", cOptions, ttsOptions, callback)
+	if err != nil {
+		fmt.Println("ERROR creating TTS connection:", err)
+		return
+	}
+
+	// connect the websocket to Deepgram
+	bConnected := dgClient.Connect()
+	if !bConnected {
+		fmt.Println("Client.Connect failed")
+		os.Exit(1)
+	}
+
+	// Simulate user input to reset the buffer, flush, send new text, or just exit
+	time.Sleep(2 * time.Second)
+	fmt.Printf("\n\nPress 'r' and ENTER to reset the buffer, 'f' and ENTER to flush, enter new text to send it, or just ENTER to exit...\n\n> ")
+	input := bufio.NewScanner(os.Stdin)
+	for input.Scan() {
+		switch input.Text() {
+		case "r":
+			err = dgClient.Reset()
+			if err != nil {
+				fmt.Printf("Error resetting buffer: %v\n", err)
+			} else {
+				fmt.Println("Buffer reset successfully.")
+			}
+		case "f":
+			err = dgClient.Flush()
+			if err != nil {
+				fmt.Printf("Error flushing buffer: %v\n", err)
+			} else {
+				fmt.Println("Buffer flushed successfully.")
+			}
+		case "":
+			goto EXIT
+		default:
+			err = dgClient.SpeakWithText(input.Text())
+			if err != nil {
+				fmt.Printf("Error sending text input: %v\n", err)
+			} else {
+				fmt.Println("Text sent successfully.")
+			}
+			fmt.Printf("\n\nPress 'r' and ENTER to reset the buffer, 'f' and ENTER to flush, enter new text to send it, or just ENTER to exit...\n\n> ")
+		}
+	}
+
+EXIT:
+
+	// close the connection
+	dgClient.Stop()
+
+	fmt.Printf("Program exiting...\n")
+}
diff --git a/examples/text-to-speech/websocket/simple/main.go b/examples/text-to-speech/websocket/simple/main.go
@@ -0,0 +1,138 @@
+// Copyright 2024 Deepgram SDK contributors. All Rights Reserved.
+// Use of this source code is governed by a MIT license that can be found in the LICENSE file.
+// SPDX-License-Identifier: MIT
+
+package main
+
+import (
+	"context"
+	"fmt"
+	"os"
+	"strings"
+	"time"
+
+	msginterfaces "github.com/deepgram/deepgram-go-sdk/pkg/api/speak/v1/websocket/interfaces"
+	interfaces "github.com/deepgram/deepgram-go-sdk/pkg/client/interfaces/v1"
+	speak "github.com/deepgram/deepgram-go-sdk/pkg/client/speak"
+)
+
+const (
+	API_KEY    = ""
+	TTS_TEXT   = "Hello, this is a text to speech example using Deepgram."
+	AUDIO_FILE = "output.mp3"
+)
+
+// Implement your own callback
+type MyCallback struct{}
+
+func (c MyCallback) Metadata(md *msginterfaces.MetadataResponse) error {
+	fmt.Printf("\n[Metadata] Received\n")
+	fmt.Printf("Metadata.RequestID: %s\n", strings.TrimSpace(md.RequestID))
+	return nil
+}
+
+func (c MyCallback) Binary(byMsg []byte) error {
+	fmt.Printf("\n[Binary] Received\n")
+
+	file, err := os.OpenFile(AUDIO_FILE, os.O_CREATE|os.O_APPEND|os.O_WRONLY, 0o666)
+	if err != nil {
+		fmt.Printf("Error creating file %s: %v\n", AUDIO_FILE, err)
+		return err
+	}
+	defer file.Close()
+
+	_, err = file.Write(byMsg)
+	if err != nil {
+		fmt.Printf("Error writing audio data to file: %v\n", err)
+		return err
+	}
+
+	fmt.Printf("Audio data saved to %s\n", AUDIO_FILE)
+	return nil
+}
+
+func (c MyCallback) Flush(fl *msginterfaces.FlushedResponse) error {
+	fmt.Printf("\n[Flushed] Received\n")
+	return nil
+}
+
+func (c MyCallback) Warning(wr *msginterfaces.WarningResponse) error {
+	fmt.Printf("\n[Warning] Received\n")
+	fmt.Printf("Warning.Code: %s\n", wr.WarnCode)
+	fmt.Printf("Warning.Description: %s\n\n", wr.WarnMsg)
+	return nil
+}
+
+func (c MyCallback) Error(er *msginterfaces.ErrorResponse) error {
+	fmt.Printf("\n[Error] Received\n")
+	fmt.Printf("Error.Code: %s\n", er.ErrCode)
+	fmt.Printf("Error.Description: %s\n\n", er.ErrMsg)
+	return nil
+}
+
+func (c MyCallback) Close(cr *msginterfaces.CloseResponse) error {
+	fmt.Printf("\n[Close] Received\n")
+	return nil
+}
+
+func (c MyCallback) Open(or *msginterfaces.OpenResponse) error {
+	fmt.Printf("\n[Open] Received\n")
+	return nil
+}
+
+func main() {
+	// init library
+	speak.Init(speak.InitLib{
+		LogLevel: speak.LogLevelDefault, // LogLevelDefault, LogLevelFull, LogLevelDebug, LogLevelTrace
+	})
+
+	// Go context
+	ctx := context.Background()
+
+	// set the Client options
+	cOptions := &interfaces.ClientOptions{}
+
+	// set the TTS options
+	ttsOptions := &interfaces.SpeakOptions{
+		Model: "aura-asteria-en",
+	}
+
+	// create the callback
+	callback := MyCallback{}
+
+	// create a new stream using the NewStream function
+	dgClient, err := speak.NewWebSocket(ctx, "", cOptions, ttsOptions, callback)
+	if err != nil {
+		fmt.Println("ERROR creating TTS connection:", err)
+		return
+	}
+
+	// connect the websocket to Deepgram
+	bConnected := dgClient.Connect()
+	if !bConnected {
+		fmt.Println("Client.Connect failed")
+		os.Exit(1)
+	}
+
+	// Send the text input
+	err = dgClient.SpeakWithText(TTS_TEXT)
+	if err != nil {
+		fmt.Printf("Error sending text input: %v\n", err)
+		return
+	}
+
+	// Flush the text input
+	err = dgClient.Flush()
+	if err != nil {
+		fmt.Printf("Error sending text input: %v\n", err)
+		return
+	}
+
+	// wait for user input to exit
+	time.Sleep(5 * time.Second)
+
+	// close the connection
+	dgClient.Stop()
+
+	fmt.Printf("Program exiting...\n")
+}
diff --git a/pkg/api/speak/v1/websocket/constants.go b/pkg/api/speak/v1/websocket/constants.go
@@ -0,0 +1,25 @@
+// Copyright 2024 Deepgram SDK contributors. All Rights Reserved.
+// Use of this source code is governed by a MIT license that can be found in the LICENSE file.
+// SPDX-License-Identifier: MIT
+
+package websocketv1
+
+import (
+	"errors"
+)
+
+const (
+	PackageVersion string = "v1.0"
+)
+
+// errors
+var (
+	// ErrInvalidInput required input was not found
+	ErrInvalidInput = errors.New("required input was not found")
+
+	// ErrInvalidMessageType invalid message type
+	ErrInvalidMessageType = errors.New("invalid message type")
+
+	// ErrUserCallbackNotDefined user callback object not defined
+	ErrUserCallbackNotDefined = errors.New("user callback object not defined")
+)