93 lines
2.6 KiB
Go
93 lines
2.6 KiB
Go
|
package eino
|
|||
|
|
|
|||
|
|
import (
|
|||
|
|
"context"
|
|||
|
|
"encoding/base64"
|
|||
|
|
|
|||
|
|
"github.com/cloudwego/eino/compose"
|
|||
|
|
|
|||
|
|
"github.com/hhs/camtalk/internal/ai/tts"
|
|||
|
|
"github.com/hhs/camtalk/internal/logger"
|
|||
|
|
"github.com/hhs/camtalk/internal/models"
|
|||
|
|
)
|
|||
|
|
|
|||
|
|
// NewTTSLambda 创建 TTS Lambda 节点。
|
|||
|
|
// 输入: []string（句子数组，框架自动从 StreamReader concat）→ 输出: struct{}
|
|||
|
|
//
|
|||
|
|
// 将句子数组转为 channel，调用 ttsService.SynthesizeStream() 流式合成，
|
|||
|
|
// 逐 chunk 推送 tts_audio 到客户端。TTS 失败静默跳过。
|
|||
|
|
func NewTTSLambda(ttsService tts.Service, ttsVoice string, ttsSpeed float64, ttsOutputFmt string, ttsSampleRate int) *compose.Lambda {
|
|||
|
|
return compose.InvokableLambda(func(ctx context.Context, sentences []string) (struct{}, error) {
|
|||
|
|
log := logger.Log
|
|||
|
|
sender := senderFromCtx(ctx)
|
|||
|
|
requestID := requestIDFromCtx(ctx)
|
|||
|
|
state := stateFromCtx(ctx)
|
|||
|
|
|
|||
|
|
// 检查 TTS 是否启用（从 State 或 context 获取）
|
|||
|
|
// TTSEnabled 信息在 PipelineInput 中，通过 State 传递
|
|||
|
|
if state != nil {
|
|||
|
|
state.mu.Lock()
|
|||
|
|
ttsEnabled := true // 默认启用，由适配器通过 State 设置
|
|||
|
|
state.mu.Unlock()
|
|||
|
|
if !ttsEnabled {
|
|||
|
|
return struct{}{}, nil
|
|||
|
|
}
|
|||
|
|
}
|
|||
|
|
|
|||
|
|
if len(sentences) == 0 {
|
|||
|
|
return struct{}{}, nil
|
|||
|
|
}
|
|||
|
|
|
|||
|
|
if sender == nil || requestID == "" {
|
|||
|
|
return struct{}{}, nil
|
|||
|
|
}
|
|||
|
|
|
|||
|
|
log.Infow("开始 TTS 合成", "request_id", requestID, "sentence_count", len(sentences))
|
|||
|
|
|
|||
|
|
// 将句子数组转为 channel（ttsService.SynthesizeStream 需要 <-chan string）
|
|||
|
|
sentenceCh := make(chan string, len(sentences))
|
|||
|
|
for _, s := range sentences {
|
|||
|
|
sentenceCh <- s
|
|||
|
|
}
|
|||
|
|
close(sentenceCh)
|
|||
|
|
|
|||
|
|
// 调用 TTS 服务
|
|||
|
|
ttsStream, err := ttsService.SynthesizeStream(ctx, sentenceCh, tts.Options{
|
|||
|
|
Voice: ttsVoice,
|
|||
|
|
Speed: ttsSpeed,
|
|||
|
|
OutputFmt: ttsOutputFmt,
|
|||
|
|
SampleRate: ttsSampleRate,
|
|||
|
|
})
|
|||
|
|
if err != nil {
|
|||
|
|
log.Errorw("TTS 合成启动失败（已跳过）", "error", err, "request_id", requestID)
|
|||
|
|
return struct{}{}, nil // TTS 失败不中断流程
|
|||
|
|
}
|
|||
|
|
|
|||
|
|
// 消费 TTS 音频流，推送到客户端
|
|||
|
|
for chunk := range ttsStream {
|
|||
|
|
select {
|
|||
|
|
case <-ctx.Done():
|
|||
|
|
log.Infow("TTS 流被中断", "request_id", requestID)
|
|||
|
|
return struct{}{}, ctx.Err()
|
|||
|
|
default:
|
|||
|
|
}
|
|||
|
|
|
|||
|
|
audioBase64 := base64.StdEncoding.EncodeToString(chunk.Audio)
|
|||
|
|
|
|||
|
|
if err := sender.SendTTSAudio(models.WsTTSAudio{
|
|||
|
|
Type: "tts_audio",
|
|||
|
|
RequestID: requestID,
|
|||
|
|
Audio: audioBase64,
|
|||
|
|
MimeType: "audio/mp3",
|
|||
|
|
IsLast: chunk.IsLast,
|
|||
|
|
Final: chunk.Final,
|
|||
|
|
}); err != nil {
|
|||
|
|
log.Errorw("发送 tts_audio 失败", "error", err)
|
|||
|
|
}
|
|||
|
|
}
|
|||
|
|
|
|||
|
|
log.Infow("TTS 合成完成", "request_id", requestID)
|
|||
|
|
return struct{}{}, nil
|
|||
|
|
})
|
|||
|
|
}
|