diff --git a/main/manager-api/src/main/resources/db/changelog/202507101201.sql b/main/manager-api/src/main/resources/db/changelog/202507101201.sql deleted file mode 100644 index 14bd6725..00000000 --- a/main/manager-api/src/main/resources/db/changelog/202507101201.sql +++ /dev/null @@ -1,31 +0,0 @@ --- OpenAI ASR模型供应器 -delete from `ai_model_provider` where id = 'SYSTEM_ASR_GptASR'; -INSERT INTO `ai_model_provider` (`id`, `model_type`, `provider_code`, `name`, `fields`, `sort`, `creator`, `create_date`, `updater`, `update_date`) VALUES -('SYSTEM_ASR_GptASR', 'ASR', 'gpt', 'Gpt语音识别', '[{"key": "base_url", "type": "string", "label": "基础URL"}, {"key": "model_name", "type": "string", "label": "模型名称"}, {"key": "api_key", "type": "string", "label": "API密钥"}, {"key": "output_dir", "type": "string", "label": "输出目录"}]', 5, 1, NOW(), 1, NOW()); - - --- OpenAI ASR模型配置 -delete from `ai_model_config` where id = 'ASR_GptASR'; -INSERT INTO `ai_model_config` VALUES ('ASR_GptASR', 'ASR', 'GptASR', 'GPT语音识别', 0, 1, '{\"type\": \"gpt\", \"api_key\": \"\", \"base_url\": \"https://api.openai.com/v1/audio/transcriptions\", \"model_name\": \"gpt-4o-mini-transcribe\", \"output_dir\": \"tmp/\"}', NULL, NULL, 3, NULL, NULL, NULL, NULL); - - --- 更新OpenAI ASR配置说明 -UPDATE `ai_model_config` SET -`doc_link` = 'https://platform.openai.com/docs/api-reference/audio/createTranscription', -`remark` = 'OpenAI ASR配置说明： -1. 需要在OpenAI开放平台创建组织并获取api_key -2. 支持中、英、日、韩等多种语音识别，具体参考文档https://platform.openai.com/docs/guides/speech-to-text -3. 需要网络连接 -4. 输出文件保存在tmp/目录 -5. 兼容groq语音识别。 groq识别速度更快。具体参考文档：https://console.groq.com/docs/speech-to-text -申请步骤： -**OpenAi ASR申请步骤：** -1.登录OpenAI Platform。https://auth.openai.com/log-in -2.创建api-key https://platform.openai.com/settings/organization/api-keys -3.模型可以选择gpt-4o-transcribe或GPT-4o mini Transcribe -**groq ASR申请步骤：** -1.登录groq Console。https://console.groq.com/home -2.创建api-key https://console.groq.com/keys -3.模型可以选择whisper-large-v3-turbo或whisper-large-v3（distil-whisper-large-v3-en仅支持英语转录） -4.base url https://api.groq.com/openai/v1/audio/transcriptions -' WHERE `id` = 'ASR_GptASR'; \ No newline at end of file diff --git a/main/manager-api/src/main/resources/db/changelog/202507101203.sql b/main/manager-api/src/main/resources/db/changelog/202507101203.sql new file mode 100644 index 00000000..66896ef8 --- /dev/null +++ b/main/manager-api/src/main/resources/db/changelog/202507101203.sql @@ -0,0 +1,38 @@ +-- OpenAI ASR模型供应器 +delete from `ai_model_provider` where id = 'SYSTEM_ASR_OpenaiASR'; +INSERT INTO `ai_model_provider` (`id`, `model_type`, `provider_code`, `name`, `fields`, `sort`, `creator`, `create_date`, `updater`, `update_date`) VALUES +('SYSTEM_ASR_OpenaiASR', 'ASR', 'openai', 'OpenAI语音识别', '[{"key": "base_url", "type": "string", "label": "基础URL"}, {"key": "model_name", "type": "string", "label": "模型名称"}, {"key": "api_key", "type": "string", "label": "API密钥"}, {"key": "output_dir", "type": "string", "label": "输出目录"}]', 9, 1, NOW(), 1, NOW()); + + +-- OpenAI ASR模型配置 +delete from `ai_model_config` where id = 'ASR_OpenaiASR'; +INSERT INTO `ai_model_config` VALUES ('ASR_OpenaiASR', 'ASR', 'OpenaiASR', 'OpenAI语音识别', 0, 1, '{\"type\": \"openai\", \"api_key\": \"\", \"base_url\": \"https://api.openai.com/v1/audio/transcriptions\", \"model_name\": \"gpt-4o-mini-transcribe\", \"output_dir\": \"tmp/\"}', NULL, NULL, 9, NULL, NULL, NULL, NULL); + +-- groq ASR模型配置 +delete from `ai_model_config` where id = 'ASR_GroqASR'; +INSERT INTO `ai_model_config` VALUES ('ASR_GroqASR', 'ASR', 'GroqASR', 'Groq语音识别', 0, 1, '{\"type\": \"openai\", \"api_key\": \"\", \"base_url\": \"https://api.groq.com/openai/v1/audio/transcriptions\", \"model_name\": \"whisper-large-v3-turbo\", \"output_dir\": \"tmp/\"}', NULL, NULL, 10, NULL, NULL, NULL, NULL); + + +-- 更新OpenAI ASR配置说明 +UPDATE `ai_model_config` SET +`doc_link` = 'https://platform.openai.com/docs/api-reference/audio/createTranscription', +`remark` = 'OpenAI ASR配置说明： +1. 需要在OpenAI开放平台创建组织并获取api_key +2. 支持中、英、日、韩等多种语音识别，具体参考文档https://platform.openai.com/docs/guides/speech-to-text +3. 需要网络连接 +4. 输出文件保存在tmp/目录 +申请步骤： +**OpenAi ASR申请步骤：** +1.登录OpenAI Platform。https://auth.openai.com/log-in +2.创建api-key https://platform.openai.com/settings/organization/api-keys +3.模型可以选择gpt-4o-transcribe或GPT-4o mini Transcribe +' WHERE `id` = 'ASR_OpenaiASR'; + +-- 更新Groq ASR配置说明 +UPDATE `ai_model_config` SET +`doc_link` = 'https://console.groq.com/docs/speech-to-text', +`remark` = 'Groq ASR配置说明： +1.登录groq Console。https://console.groq.com/home +2.创建api-key https://console.groq.com/keys +3.模型可以选择whisper-large-v3-turbo或whisper-large-v3（distil-whisper-large-v3-en仅支持英语转录） +' WHERE `id` = 'ASR_GroqASR'; \ No newline at end of file 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 1f10285f..72000ee3 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 @@ -241,12 +241,12 @@ databaseChangeLog: encoding: utf8 path: classpath:db/changelog/202506261637.sql - changeSet: - id: 202507101201 + id: 202507101203 author: luruxian changes: - sqlFile: encoding: utf8 - path: classpath:db/changelog/202507101201.sql + path: classpath:db/changelog/202507101203.sql - changeSet: id: 202507071130 author: cgd diff --git a/main/xiaozhi-server/config.yaml b/main/xiaozhi-server/config.yaml index 741d6d18..ccfd4176 100644 --- a/main/xiaozhi-server/config.yaml +++ b/main/xiaozhi-server/config.yaml @@ -355,7 +355,33 @@ ASR: # 语言参数，1537为普通话，具体参考：https://ai.baidu.com/ai-doc/SPEECH/0lbxfnc9b dev_pid: 1537 output_dir: tmp/ + OpenaiASR: + # OpenAI语音识别服务，需要先在OpenAI平台创建组织并获取api_key + # 支持中、英、日、韩等多种语音识别，具体参考文档https://platform.openai.com/docs/guides/speech-to-text + # 需要网络连接 + # 申请步骤： + # 1.登录OpenAI Platform。https://auth.openai.com/log-in + # 2.创建api-key https://platform.openai.com/settings/organization/api-keys + # 3.模型可以选择gpt-4o-transcribe或GPT-4o mini Transcribe + type: openai + api_key: 你的OpenAI API密钥 + base_url: https://api.openai.com/v1/audio/transcriptions + model_name: gpt-4o-mini-transcribe + output_dir: tmp/ + GroqASR: + # Groq语音识别服务，需要先在Groq Console创建API密钥 + # 申请步骤： + # 1.登录groq Console。https://console.groq.com/home + # 2.创建api-key https://console.groq.com/keys + # 3.模型可以选择whisper-large-v3-turbo或whisper-large-v3（distil-whisper-large-v3-en仅支持英语转录） + type: openai + api_key: 你的Groq API密钥 + base_url: https://api.groq.com/openai/v1/audio/transcriptions + model_name: whisper-large-v3-turbo + output_dir: tmp/ + + VAD: SileroVAD: type: silero diff --git a/main/xiaozhi-server/core/providers/asr/gpt.py b/main/xiaozhi-server/core/providers/asr/openai.py similarity index 100% rename from main/xiaozhi-server/core/providers/asr/gpt.py rename to main/xiaozhi-server/core/providers/asr/openai.py