From 155ba92ba68bcde8d2bca8b472f4d1f228689cf3 Mon Sep 17 00:00:00 2001 From: CGD <3030332422@qq.com> Date: Mon, 7 Jul 2025 15:29:13 +0800 Subject: [PATCH] =?UTF-8?q?update:=E5=A2=9E=E5=8A=A0=E4=BA=86=E6=99=BA?= =?UTF-8?q?=E6=8E=A7=E5=8F=B0=E7=9A=84sql=E8=AF=AD=E5=8F=A5=EF=BC=8C?= =?UTF-8?q?=E4=BC=98=E5=8C=96=E4=BA=86=E9=83=A8=E5=88=86=E9=85=8D=E7=BD=AE?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- .../{202505081146.sql => 202505081147.sql} | 2 +- .../resources/db/changelog/202507071130.sql | 26 +++++++++ .../resources/db/changelog/202507071530.sql | 56 +++++++++++++++++++ .../db/changelog/db.changelog-master.yaml | 20 ++++++- main/xiaozhi-server/config.yaml | 10 ++-- .../core/providers/asr/aliyun_stream.py | 2 +- 6 files changed, 107 insertions(+), 9 deletions(-) rename main/manager-api/src/main/resources/db/changelog/{202505081146.sql => 202505081147.sql} (97%) create mode 100644 main/manager-api/src/main/resources/db/changelog/202507071130.sql create mode 100644 main/manager-api/src/main/resources/db/changelog/202507071530.sql diff --git a/main/manager-api/src/main/resources/db/changelog/202505081146.sql b/main/manager-api/src/main/resources/db/changelog/202505081147.sql similarity index 97% rename from main/manager-api/src/main/resources/db/changelog/202505081146.sql rename to main/manager-api/src/main/resources/db/changelog/202505081147.sql index fe7582f3..1a561bda 100644 --- a/main/manager-api/src/main/resources/db/changelog/202505081146.sql +++ b/main/manager-api/src/main/resources/db/changelog/202505081147.sql @@ -1,6 +1,6 @@ -- 添加百度ASR模型配置 delete from `ai_model_config` where `id` = 'ASR_BaiduASR'; -INSERT INTO `ai_model_config` VALUES ('ASR_BaiduASR', 'ASR', 'BaiduASR', '百度语音识别', 0, 1, '{\"type\": \"baidu\", \"app_id\": \"\", \"api_key\": \"\", \"secret_key\": \"\", \"dev_pid\": 1537, \"output_dir\": \"tmp/\"}', NULL, NULL, 7, NULL, NULL, NULL, NULL); +INSERT INTO `ai_model_config` VALUES ('ASR_BaiduASR', 'ASR', 'BaiduASR', '百度语音识别', 0, 1, '{\"type\": \"baidu\", \"app_id\": \"\", \"api_key\": \"\", \"secret_key\": \"\", \"dev_pid\": 1537, \"output_dir\": \"tmp/\"}', NULL, NULL, 8, NULL, NULL, NULL, NULL); -- 添加百度ASR供应器 diff --git a/main/manager-api/src/main/resources/db/changelog/202507071130.sql b/main/manager-api/src/main/resources/db/changelog/202507071130.sql new file mode 100644 index 00000000..008d624e --- /dev/null +++ b/main/manager-api/src/main/resources/db/changelog/202507071130.sql @@ -0,0 +1,26 @@ +-- 添加阿里云流式ASR供应器 +delete from `ai_model_provider` where id = 'SYSTEM_ASR_AliyunStreamASR'; +INSERT INTO `ai_model_provider` (`id`, `model_type`, `provider_code`, `name`, `fields`, `sort`, `creator`, `create_date`, `updater`, `update_date`) VALUES +('SYSTEM_ASR_AliyunStreamASR', 'ASR', 'aliyun_stream', '阿里云语音识别(流式)', '[{"key":"appkey","label":"应用AppKey","type":"string"},{"key":"token","label":"临时Token","type":"string"},{"key":"access_key_id","label":"AccessKey ID","type":"string"},{"key":"access_key_secret","label":"AccessKey Secret","type":"string"},{"key":"host","label":"服务地址","type":"string"},{"key":"max_sentence_silence","label":"断句检测时间","type":"number"},{"key":"output_dir","label":"输出目录","type":"string"}]', 6, 1, NOW(), 1, NOW()); + +-- 添加阿里云流式ASR模型配置 +delete from `ai_model_config` where id = 'ASR_AliyunStreamASR'; +INSERT INTO `ai_model_config` VALUES ('ASR_AliyunStreamASR', 'ASR', 'AliyunStreamASR', '阿里云语音识别(流式)', 0, 1, '{\"type\": \"aliyun_stream\", \"appkey\": \"\", \"token\": \"\", \"access_key_id\": \"\", \"access_key_secret\": \"\", \"host\": \"nls-gateway-cn-shanghai.aliyuncs.com\", \"max_sentence_silence\": 800, \"output_dir\": \"tmp/\"}', NULL, NULL, 7, NULL, NULL, NULL, NULL); + +-- 更新阿里云流式ASR配置说明 +UPDATE `ai_model_config` SET +`doc_link` = 'https://nls-portal.console.aliyun.com/', +`remark` = '阿里云流式ASR配置说明： +1. 阿里云ASR和阿里云(流式)ASR的区别是：阿里云ASR是一次性识别，阿里云(流式)ASR是实时流式识别 +2. 流式ASR具有更低的延迟和更好的实时性，适合语音交互场景 +3. 需要在阿里云智能语音交互控制台创建应用并获取认证信息 +4. 支持中文实时语音识别，支持标点符号预测和逆文本规范化 +5. 需要网络连接，输出文件保存在tmp/目录 +申请步骤： +1. 访问 https://nls-portal.console.aliyun.com/ 开通智能语音交互服务 +2. 访问 https://nls-portal.console.aliyun.com/applist 创建项目并获取appkey +3. 访问 https://nls-portal.console.aliyun.com/overview 获取临时token（或配置access_key_id和access_key_secret自动获取） +4. 如需动态token管理，建议配置access_key_id和access_key_secret +5. max_sentence_silence参数控制断句检测时间（毫秒），默认800ms +如需了解更多参数配置，请参考：https://help.aliyun.com/zh/isi/developer-reference/real-time-speech-recognition +' WHERE `id` = 'ASR_AliyunStreamASR'; diff --git a/main/manager-api/src/main/resources/db/changelog/202507071530.sql b/main/manager-api/src/main/resources/db/changelog/202507071530.sql new file mode 100644 index 00000000..ed3dcf49 --- /dev/null +++ b/main/manager-api/src/main/resources/db/changelog/202507071530.sql @@ -0,0 +1,56 @@ +-- 添加阿里云流式TTS供应器 +delete from `ai_model_provider` where id = 'SYSTEM_TTS_AliyunStreamTTS'; +INSERT INTO `ai_model_provider` (`id`, `model_type`, `provider_code`, `name`, `fields`, `sort`, `creator`, `create_date`, `updater`, `update_date`) VALUES +('SYSTEM_TTS_AliyunStreamTTS', 'TTS', 'aliyun_stream', '阿里云语音合成(流式)', '[{"key":"appkey","label":"应用AppKey","type":"string"},{"key":"token","label":"临时Token","type":"string"},{"key":"access_key_id","label":"AccessKey ID","type":"string"},{"key":"access_key_secret","label":"AccessKey Secret","type":"string"},{"key":"host","label":"服务地址","type":"string"},{"key":"voice","label":"默认音色","type":"string"},{"key":"format","label":"音频格式","type":"string"},{"key":"sample_rate","label":"采样率","type":"number"},{"key":"volume","label":"音量","type":"number"},{"key":"speech_rate","label":"语速","type":"number"},{"key":"pitch_rate","label":"音调","type":"number"},{"key":"output_dir","label":"输出目录","type":"string"}]', 15, 1, NOW(), 1, NOW()); + +-- 添加阿里云流式TTS模型配置 +delete from `ai_model_config` where id = 'TTS_AliyunStreamTTS'; +INSERT INTO `ai_model_config` VALUES ('TTS_AliyunStreamTTS', 'TTS', 'AliyunStreamTTS', '阿里云语音合成(流式)', 0, 1, '{\"type\": \"aliyun_stream\", \"appkey\": \"\", \"token\": \"\", \"access_key_id\": \"\", \"access_key_secret\": \"\", \"host\": \"nls-gateway-cn-beijing.aliyuncs.com\", \"voice\": \"longxiaochun\", \"format\": \"pcm\", \"sample_rate\": 16000, \"volume\": 50, \"speech_rate\": 0, \"pitch_rate\": 0, \"output_dir\": \"tmp/\"}', NULL, NULL, 18, NULL, NULL, NULL, NULL); + +-- 更新阿里云流式TTS配置说明 +UPDATE `ai_model_config` SET +`doc_link` = 'https://nls-portal.console.aliyun.com/', +`remark` = '阿里云流式TTS配置说明： +1. 阿里云TTS和阿里云(流式)TTS的区别是：阿里云TTS是一次性合成，阿里云(流式)TTS是实时流式合成 +2. 流式TTS具有更低的延迟和更好的实时性，适合语音交互场景 +3. 需要在阿里云智能语音交互控制台创建应用并获取认证信息 +4. 支持CosyVoice大模型音色，音质更加自然 +5. 支持实时调节音量、语速、音调等参数 +申请步骤： +1. 访问 https://nls-portal.console.aliyun.com/ 开通智能语音交互服务 +2. 访问 https://nls-portal.console.aliyun.com/applist 创建项目并获取appkey +3. 访问 https://nls-portal.console.aliyun.com/overview 获取临时token（或配置access_key_id和access_key_secret自动获取） +4. 如需动态token管理，建议配置access_key_id和access_key_secret +5. 可选择北京、上海等不同地域的服务器以优化延迟 +6. voice参数支持CosyVoice大模型音色，如longxiaochun、longyueyue等 +如需了解更多参数配置，请参考：https://help.aliyun.com/zh/isi/developer-reference/real-time-speech-synthesis +' WHERE `id` = 'TTS_AliyunStreamTTS'; + +-- 添加阿里云流式TTS音色 +delete from `ai_tts_voice` where tts_model_id = 'TTS_AliyunStreamTTS'; +-- 温柔女声系列 +INSERT INTO `ai_tts_voice` VALUES ('TTS_AliyunStreamTTS_0001', 'TTS_AliyunStreamTTS', '龙小淳-温柔姐姐', 'longxiaochun', '中文及中英文混合', NULL, NULL, 1, NULL, NULL, NULL, NULL); +INSERT INTO `ai_tts_voice` VALUES ('TTS_AliyunStreamTTS_0002', 'TTS_AliyunStreamTTS', '龙小夏-温柔女声', 'longxiaoxia', '中文及中英文混合', NULL, NULL, 2, NULL, NULL, NULL, NULL); +INSERT INTO `ai_tts_voice` VALUES ('TTS_AliyunStreamTTS_0003', 'TTS_AliyunStreamTTS', '龙玫-温柔女声', 'longmei', '中文及中英文混合', NULL, NULL, 3, NULL, NULL, NULL, NULL); +INSERT INTO `ai_tts_voice` VALUES ('TTS_AliyunStreamTTS_0004', 'TTS_AliyunStreamTTS', '龙瑰-温柔女声', 'longgui', '中文及中英文混合', NULL, NULL, 4, NULL, NULL, NULL, NULL); +-- 御姐女声系列 +INSERT INTO `ai_tts_voice` VALUES ('TTS_AliyunStreamTTS_0005', 'TTS_AliyunStreamTTS', '龙玉-御姐女声', 'longyu', '中文及中英文混合', NULL, NULL, 5, NULL, NULL, NULL, NULL); +INSERT INTO `ai_tts_voice` VALUES ('TTS_AliyunStreamTTS_0006', 'TTS_AliyunStreamTTS', '龙娇-御姐女声', 'longjiao', '中文及中英文混合', NULL, NULL, 6, NULL, NULL, NULL, NULL); +-- 男声系列 +INSERT INTO `ai_tts_voice` VALUES ('TTS_AliyunStreamTTS_0007', 'TTS_AliyunStreamTTS', '龙臣-译制片男声', 'longchen', '中文及中英文混合', NULL, NULL, 7, NULL, NULL, NULL, NULL); +INSERT INTO `ai_tts_voice` VALUES ('TTS_AliyunStreamTTS_0008', 'TTS_AliyunStreamTTS', '龙修-青年男声', 'longxiu', '中文及中英文混合', NULL, NULL, 8, NULL, NULL, NULL, NULL); +INSERT INTO `ai_tts_voice` VALUES ('TTS_AliyunStreamTTS_0009', 'TTS_AliyunStreamTTS', '龙橙-阳光男声', 'longcheng', '中文及中英文混合', NULL, NULL, 9, NULL, NULL, NULL, NULL); +INSERT INTO `ai_tts_voice` VALUES ('TTS_AliyunStreamTTS_0010', 'TTS_AliyunStreamTTS', '龙哲-成熟男声', 'longzhe', '中文及中英文混合', NULL, NULL, 10, NULL, NULL, NULL, NULL); +-- 专业播报系列 +INSERT INTO `ai_tts_voice` VALUES ('TTS_AliyunStreamTTS_0011', 'TTS_AliyunStreamTTS', 'Bella2.0-新闻女声', 'loongbella', '中文及中英文混合', NULL, NULL, 11, NULL, NULL, NULL, NULL); +INSERT INTO `ai_tts_voice` VALUES ('TTS_AliyunStreamTTS_0012', 'TTS_AliyunStreamTTS', 'Stella2.0-飒爽女声', 'loongstella', '中文及中英文混合', NULL, NULL, 12, NULL, NULL, NULL, NULL); +INSERT INTO `ai_tts_voice` VALUES ('TTS_AliyunStreamTTS_0013', 'TTS_AliyunStreamTTS', '龙书-新闻男声', 'longshu', '中文及中英文混合', NULL, NULL, 13, NULL, NULL, NULL, NULL); +INSERT INTO `ai_tts_voice` VALUES ('TTS_AliyunStreamTTS_0014', 'TTS_AliyunStreamTTS', '龙婧-严肃女声', 'longjing', '中文及中英文混合', NULL, NULL, 14, NULL, NULL, NULL, NULL); +-- 特色音色系列 +INSERT INTO `ai_tts_voice` VALUES ('TTS_AliyunStreamTTS_0015', 'TTS_AliyunStreamTTS', '龙奇-活泼童声', 'longqi', '中文及中英文混合', NULL, NULL, 15, NULL, NULL, NULL, NULL); +INSERT INTO `ai_tts_voice` VALUES ('TTS_AliyunStreamTTS_0016', 'TTS_AliyunStreamTTS', '龙华-活泼女童', 'longhua', '中文及中英文混合', NULL, NULL, 16, NULL, NULL, NULL, NULL); +INSERT INTO `ai_tts_voice` VALUES ('TTS_AliyunStreamTTS_0017', 'TTS_AliyunStreamTTS', '龙无-无厘头男声', 'longwu', '中文及中英文混合', NULL, NULL, 17, NULL, NULL, NULL, NULL); +INSERT INTO `ai_tts_voice` VALUES ('TTS_AliyunStreamTTS_0018', 'TTS_AliyunStreamTTS', '龙大锤-幽默男声', 'longdachui', '中文及中英文混合', NULL, NULL, 18, NULL, NULL, NULL, NULL); +-- 粤语系列 +INSERT INTO `ai_tts_voice` VALUES ('TTS_AliyunStreamTTS_0019', 'TTS_AliyunStreamTTS', '龙嘉怡-粤语女声', 'longjiayi', '粤语及粤英混合', NULL, NULL, 19, NULL, NULL, NULL, NULL); +INSERT INTO `ai_tts_voice` VALUES ('TTS_AliyunStreamTTS_0020', 'TTS_AliyunStreamTTS', '龙桃-粤语女声', 'longtao', '粤语及粤英混合', NULL, NULL, 20, NULL, NULL, NULL, NULL); diff --git a/main/manager-api/src/main/resources/db/changelog/db.changelog-master.yaml b/main/manager-api/src/main/resources/db/changelog/db.changelog-master.yaml index b60094ef..3852c545 100755 --- a/main/manager-api/src/main/resources/db/changelog/db.changelog-master.yaml +++ b/main/manager-api/src/main/resources/db/changelog/db.changelog-master.yaml @@ -101,12 +101,12 @@ databaseChangeLog: encoding: utf8 path: classpath:db/changelog/202505022134.sql - changeSet: - id: 202505081146 + id: 202505081147 author: hrz changes: - sqlFile: encoding: utf8 - path: classpath:db/changelog/202505081146.sql + path: classpath:db/changelog/202505081147.sql - changeSet: id: 202505091555 author: whosmyqueen @@ -225,4 +225,18 @@ databaseChangeLog: changes: - sqlFile: encoding: utf8 - path: classpath:db/changelog/202506261637.sql \ No newline at end of file + path: classpath:db/changelog/202506261637.sql + - changeSet: + id: 202507071130 + author: cgd + changes: + - sqlFile: + encoding: utf8 + path: classpath:db/changelog/202507071130.sql + - changeSet: + id: 202507071530 + author: cgd + changes: + - sqlFile: + encoding: utf8 + path: classpath:db/changelog/202507071530.sql diff --git a/main/xiaozhi-server/config.yaml b/main/xiaozhi-server/config.yaml index a4b4ccc0..be052dc4 100644 --- a/main/xiaozhi-server/config.yaml +++ b/main/xiaozhi-server/config.yaml @@ -322,13 +322,15 @@ ASR: # 一般来说非流式ASR更便宜（0.004元/秒，¥0.24/分钟） # 但是AliyunStreamASR实时性更好（0.005元/秒，¥0.3/分钟） # 定义ASR API类型 - type: aliyun + type: aliyun_stream appkey: 你的阿里云智能语音交互服务项目Appkey token: 你的阿里云智能语音交互服务AccessToken，临时的24小时，要长期用下方的access_key_id，access_key_secret access_key_id: 你的阿里云账号access_key_id access_key_secret: 你的阿里云账号access_key_secret - # 服务器地域选择，如nls-gateway-cn-hangzhou.aliyuncs.com(杭州)等 - host: 根据自己的地理位置选择最近的服务器地域，不填默认为nls-gateway-cn-shanghai.aliyuncs.com(上海) + # 服务器地域选择，可选择距离更近的服务器以减少延迟，如nls-gateway-cn-hangzhou.aliyuncs.com(杭州)等 + host: nls-gateway-cn-shanghai.aliyuncs.com + # 断句检测时间(毫秒)，控制静音多长时间后进行断句，默认800毫秒 + max_sentence_silence: 800 output_dir: tmp/ BaiduASR: # 获取AppID、API Key、Secret Key：https://console.bce.baidu.com/ai-engine/old/#/ai/speech/app/list @@ -699,7 +701,7 @@ TTS: # appkey地址：https://nls-portal.console.aliyun.com/applist # token地址：https://nls-portal.console.aliyun.com/overview # 使用三阶段流式交互：StartSynthesis -> RunSynthesis -> StopSynthesis - type: aliyun + type: aliyun_stream output_dir: tmp/ appkey: 你的阿里云智能语音交互服务项目Appkey token: 你的阿里云智能语音交互服务AccessToken，临时的24小时，要长期用下方的access_key_id，access_key_secret diff --git a/main/xiaozhi-server/core/providers/asr/aliyun_stream.py b/main/xiaozhi-server/core/providers/asr/aliyun_stream.py index 94727798..3a41b349 100644 --- a/main/xiaozhi-server/core/providers/asr/aliyun_stream.py +++ b/main/xiaozhi-server/core/providers/asr/aliyun_stream.py @@ -123,7 +123,7 @@ class ASRProvider(ASRProviderBase): conn.asr_audio.append(audio) conn.asr_audio = conn.asr_audio[-10:] - # 参考豆包ASR：只在有声音且没有连接时建立连接 + # 只在有声音且没有连接时建立连接 if audio_have_voice and not self.is_processing: try: await self._start_recognition(conn)