feat(voice): 阿里百炼 STT/TTS 主链路接通(base64 STT + cosyvoice TTS按voice_id + REST /audio/* + voice_input.deviceId)
CI / Backend (build / vet / test / cross-compile) (push) Has been cancelled
CI / Frontend (tsc + vite build) (push) Has been cancelled

- voice/dashscope.go 新建:DashscopeSTT(qwen-audio-3.0-asr-flash, base64 data URI→text) + DashscopeTTS(cosyvoice 按 voice_id, 取非流式 24h URL 下载字节)
- cloud.go newDashboardSTT/TTS 由空 endpoint stub 改为真实百炼 adapter
- chain.go gating 从 DashscopeAPIKey!="" 改为 voiceConfigured(cfg); silent 兜底保留
- config.VoiceConfig 扩展 DASHSCOPE_BASE_URL/VOICE_STT_*/VOICE_TTS_* 字段(必填 DASHSCOPE_API_KEY)
- gateway: POST /api/v1/audio/{transcribe,speech} (owner+审计+MaxBytesReader); voiceInputRequest 增 deviceId 并透传 runner.Run
- 实测: cosyvoice-v3.5-plus+longxiaochun 回 418(引擎拒绝), 改用 cosyvoice-v3-flash+longxiaochun_v3; TTS 你好我是昔涟->106124B wav -> STT 回 你好我是西联, 链返回真实字节/文本
- 单测: dashscope_test/config voice defaults/gateway audio_test; go build/vet/test 全绿
- 声音复刻(响昔涟音色)待公网参考音频; 不做 create_voice
This commit is contained in:
Aska committed 2026-09-08 06:06:02 +08:00
1 parent d8044763ac
commit 73dabb9dde
13 files changed
+1070 -15

No files matched your search

+47
View File
@@ -162,6 +162,53 @@ func TestLoad_CapacityEnvOverrides(t *testing.T) {
}
}
func TestLoad_VoiceDefaults(t *testing.T) {
t.Setenv("JWT_SECRET", strings.Repeat("s", 40))
cfg, err := Load("")
if err != nil {
t.Fatalf("Load() error: %v", err)
}
if cfg.Voice.DashscopeBaseURL != "https://dashscope.aliyuncs.com/api/v1" {
t.Errorf("DashscopeBaseURL = %q, want the default Bailian URL", cfg.Voice.DashscopeBaseURL)
}
if cfg.Voice.STTModel != "qwen-audio-3.0-asr-flash" {
t.Errorf("STTModel = %q, want qwen-audio-3.0-asr-flash", cfg.Voice.STTModel)
}
if cfg.Voice.STTLanguage != "zh" {
t.Errorf("STTLanguage = %q, want zh", cfg.Voice.STTLanguage)
}
if cfg.Voice.TTSModel != "cosyvoice-v3-flash" {
t.Errorf("TTSModel = %q, want cosyvoice-v3-flash", cfg.Voice.TTSModel)
}
if cfg.Voice.TTSVoiceID != "longxiaochun_v3" {
t.Errorf("TTSVoiceID = %q, want longxiaochun_v3", cfg.Voice.TTSVoiceID)
}
if cfg.Voice.TTSFormat != "wav" {
t.Errorf("TTSFormat = %q, want wav", cfg.Voice.TTSFormat)
}
if cfg.Voice.TTSSampleRate != 24000 {
t.Errorf("TTSSampleRate = %d, want 24000", cfg.Voice.TTSSampleRate)
}
}
func TestLoad_VoiceEnvOverrides(t *testing.T) {
t.Setenv("JWT_SECRET", strings.Repeat("s", 40))
t.Setenv("VOICE_TTS_VOICE_ID", "custom-voice-1")
t.Setenv("VOICE_STT_MODEL", "qwen-audio-3.0-asr-flash")
cfg, err := Load("")
if err != nil {
t.Fatalf("Load() error: %v", err)
}
if cfg.Voice.TTSVoiceID != "custom-voice-1" {
t.Errorf("TTSVoiceID = %q, want custom-voice-1", cfg.Voice.TTSVoiceID)
}
if cfg.Voice.STTModel != "qwen-audio-3.0-asr-flash" {
t.Errorf("STTModel = %q, want qwen-audio-3.0-asr-flash", cfg.Voice.STTModel)
}
}
func TestParseDotEnv_QuotedAndExport(t *testing.T) {
path := writeEnvFile(t, `export FOO=bar
BAZ='quoted value'