Nik Afiq 0d58e46740
All checks were successful
CI / changes (push) Successful in 1s
CI / test (push) Successful in 6s
CI / build-ai-gateway (push) Has been skipped
CI / build-ha-gateway (push) Has been skipped
CI / build-discord-bot (push) Successful in 1m33s
CI / build-tts-gateway (push) Successful in 37s
CI / build-tts-sidecar (push) Has been skipped
feat: add /speak command for TTS integration
- Implemented the /speak command in Discord bot to synthesize speech using the TTS gateway.
- Added voice handling logic to join voice channels and play synthesized audio.
- Created tests for the new command and voice functionalities.
- Introduced TTSGateway interface for TTS service communication.
- Updated configuration to include TTS gateway address.
- Documented the TTS gateway integration and model artifact distribution process.
2026-07-25 02:09:02 +09:00

125 lines
3.7 KiB
Go

package ttsgateway
import (
"context"
"crypto/tls"
"crypto/x509"
"fmt"
"log/slog"
"os"
"path/filepath"
"time"
"gitea.nik4nao.com/nik/home-services/discord-bot/internal/logger"
ttsv1 "gitea.nik4nao.com/nik/home-services/gen/tts/v1"
"go.opentelemetry.io/contrib/instrumentation/google.golang.org/grpc/otelgrpc"
"google.golang.org/grpc"
"google.golang.org/grpc/credentials"
"google.golang.org/grpc/credentials/insecure"
)
// Client implements the app's TTS driven port over gRPC.
type Client struct {
conn *grpc.ClientConn
client ttsv1.TTSServiceClient
log *slog.Logger
}
// New constructs a gRPC client for the internal tts-gateway service.
func New(ctx context.Context, addr, tlsDir string, log *slog.Logger) (*Client, error) {
transportCreds := insecure.NewCredentials()
if tlsDir != "" {
creds, err := loadTransportCredentials(tlsDir)
if err != nil {
return nil, fmt.Errorf("load mTLS credentials: %w", err)
}
transportCreds = creds
}
conn, err := grpc.NewClient(
addr,
grpc.WithTransportCredentials(transportCreds),
grpc.WithStatsHandler(otelgrpc.NewClientHandler()),
)
if err != nil {
return nil, fmt.Errorf("dial tts-gateway: %w", err)
}
return &Client{
conn: conn,
client: ttsv1.NewTTSServiceClient(conn),
log: log,
}, nil
}
// Close closes the underlying gRPC connection.
func (c *Client) Close() error {
if err := c.conn.Close(); err != nil {
return fmt.Errorf("close tts-gateway client: %w", err)
}
return nil
}
// Synthesize forwards a speech synthesis request to tts-gateway. noise_scale/
// noise_scale_w/length_scale are left unset so tts-gateway applies its own defaults.
func (c *Client) Synthesize(ctx context.Context, speakerName, text string) ([]byte, string, error) {
start := time.Now()
log := logger.FromContext(ctx).With("grpc.method", "TTSService/Synthesize")
resp, err := c.client.Synthesize(ctx, &ttsv1.SynthesizeRequest{
SpeakerName: speakerName,
Text: text,
})
if err != nil {
log.Error("grpc call failed",
"duration_ms", time.Since(start).Milliseconds(),
"error", err.Error(),
)
return nil, "", fmt.Errorf("synthesize speech: %w", err)
}
log.Debug("grpc call completed", "duration_ms", time.Since(start).Milliseconds())
return resp.GetAudio(), resp.GetMimeType(), nil
}
// ListSpeakers returns the speaker roster from tts-gateway, optionally filtered by search.
func (c *Client) ListSpeakers(ctx context.Context, search string) ([]string, error) {
start := time.Now()
log := logger.FromContext(ctx).With("grpc.method", "TTSService/ListSpeakers")
resp, err := c.client.ListSpeakers(ctx, &ttsv1.ListSpeakersRequest{Search: search})
if err != nil {
log.Error("grpc call failed",
"duration_ms", time.Since(start).Milliseconds(),
"error", err.Error(),
)
return nil, fmt.Errorf("list tts-gateway speakers: %w", err)
}
log.Debug("grpc call completed", "duration_ms", time.Since(start).Milliseconds())
return append([]string(nil), resp.GetSpeakerNames()...), nil
}
func loadTransportCredentials(tlsDir string) (credentials.TransportCredentials, error) {
cert, err := tls.LoadX509KeyPair(
filepath.Join(tlsDir, "tls.crt"),
filepath.Join(tlsDir, "tls.key"),
)
if err != nil {
return nil, fmt.Errorf("load client key pair: %w", err)
}
caPEM, err := os.ReadFile(filepath.Join(tlsDir, "ca.crt"))
if err != nil {
return nil, fmt.Errorf("read server CA: %w", err)
}
rootCAs := x509.NewCertPool()
if !rootCAs.AppendCertsFromPEM(caPEM) {
return nil, fmt.Errorf("append server CA: invalid PEM")
}
return credentials.NewTLS(&tls.Config{
Certificates: []tls.Certificate{cert},
RootCAs: rootCAs,
ServerName: "tts-gateway.home-services.svc.cluster.local",
MinVersion: tls.VersionTLS13,
}), nil
}