Commit Graph
5 Commits
Author SHA1 Message Date
AskaEth b0fbb8bc0d docs(comments): 注释中文化 · internal/runtime/multimodal(21 文件,纯替换)
CI / Backend (build / vet / test / cross-compile) (push) Has been cancelled
CI / Frontend (tsc + vite build) (push) Has been cancelled
- 只翻注释/文档字符串,代码零变化:go/scanner 词法流比对 21 文件 token+字面量全等,增删行数 1:1(467/467)
- 刻意保留非散文英文:JSON Schema description、工具 Description() 返回值、adapter prompt、API 路径与命令示例、环境变量名
- 逐行确认代码前缀未变,未触碰其他模块
2026-10-04 12:28:16 +08:00
AskaEth 99f222761e feat(voice): 语音silent降级信号(C2) — provider仅在结果为空时出现
CI / Backend (build / vet / test / cross-compile) (push) Has been cancelled
CI / Frontend (tsc + vite build) (push) Has been cancelled
- voice/Chain+Service: STTWithProvider/TTSWithProvider(真实档位cloud/local/edge-tts/espeak/silent), 旧方法改薄包装
- gateway: transcribe空文本带{text,provider} / voice_output空音频带provider / speech空音频tts_empty+X-Voice-Provider头
- middleware: CORS Access-Control-Expose-Headers: X-Voice-Provider
- 可选接口 voiceProviderReporter(type断言透传), 自定义实现回退silent
- 新增测试10个(provider_signal/voice_signal), build/vet/test全绿+交叉编译
- Docs/api-client v0.23 + api-reference CORS 同步
2026-09-08 21:23:12 +08:00
Aska 03d7050e1e feat(voice): 百炼声音复刻create_voice + TTS instruction情绪驱动(主TTS-昔涟复刻音色)
CI / Backend (build / vet / test / cross-compile) (push) Has been cancelled
CI / Frontend (tsc + vite build) (push) Has been cancelled
2026-09-08 06:48:15 +08:00
Aska 73dabb9dde 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
2026-09-08 06:06:02 +08:00
Aska 0a936a3202 feat(multimodal): 视觉分层路由(多模态检测→主/视觉/OCR 工具)+ 语音 STT→TTS 降级链(异步) 2026-09-06 05:12:36 +08:00