chore: add ffmpeg-tools to Dockerfile for enhanced multimedia processing

fix: incorrect whisper audio usage

.dockerignore

@@ -3,4 +3,5 @@
 *.md
 .vscode
 .gitignore
-Makefile
+Makefile
+docs

.github/workflows/docker-image-arm64.yml

@@ -13,7 +13,7 @@ on:
 jobs:
   push_to_registries:
     name: Push Docker image to multiple registries
-    runs-on: ubuntu-latest
+    runs-on: self-hosted
     permissions:
       packages: write
       contents: read

.github/workflows/linux-release.yml

@@ -38,7 +38,7 @@ jobs:
       - name: Build Backend (arm64)
         run: |
           sudo apt-get update
-          sudo apt-get install gcc-aarch64-linux-gnu
+          DEBIAN_FRONTEND=noninteractive sudo apt-get install -y gcc-aarch64-linux-gnu
           CC=aarch64-linux-gnu-gcc CGO_ENABLED=1 GOOS=linux GOARCH=arm64 go build -ldflags "-s -w -X 'one-api/common.Version=$(git describe --tags)' -extldflags '-static'" -o one-api-arm64
 
       - name: Release

.github/workflows/macos-release.yml

@@ -9,7 +9,7 @@ on:
       - '!*-alpha*'
 jobs:
   release:
-    runs-on: macos-latest
+    runs-on: ubuntu-latest
     steps:
       - name: Checkout
         uses: actions/checkout@v3

.github/workflows/windows-release.yml

@@ -9,7 +9,7 @@ on:
       - '!*-alpha*'
 jobs:
   release:
-    runs-on: windows-latest
+    runs-on: ubuntu-latest
     defaults:
       run:
         shell: bash

Dockerfile

@@ -1,11 +1,11 @@
-FROM node:16 as builder
+FROM oven/bun:latest as builder
 
 WORKDIR /build
 COPY web/package.json .
-RUN npm install
+RUN bun install
 COPY ./web .
 COPY ./VERSION .
-RUN DISABLE_ESLINT_PLUGIN='true' VITE_REACT_APP_VERSION=$(cat VERSION) npm run build
+RUN DISABLE_ESLINT_PLUGIN='true' VITE_REACT_APP_VERSION=$(cat VERSION) bun run build
 
 FROM golang AS builder2
 
@@ -24,7 +24,7 @@ FROM alpine
 
 RUN apk update \
     && apk upgrade \
-    && apk add --no-cache ca-certificates tzdata \
+    && apk add --no-cache ca-certificates tzdata ffmpeg ffmpeg-tools \
     && update-ca-certificates 2>/dev/null || true
 
 COPY --from=builder2 /build/one-api /

common/model-ratio.go

@@ -32,30 +32,34 @@ var defaultModelRatio = map[string]float64{
 	"gpt-4-0613": 15,
 	"gpt-4-32k":  30,
 	//"gpt-4-32k-0314":               30, //deprecated
-	"gpt-4-32k-0613":                  30,
-	"gpt-4-1106-preview":              5,    // $10 / 1M tokens
-	"gpt-4-0125-preview":              5,    // $10 / 1M tokens
-	"gpt-4-turbo-preview":             5,    // $10 / 1M tokens
-	"gpt-4-vision-preview":            5,    // $10 / 1M tokens
-	"gpt-4-1106-vision-preview":       5,    // $10 / 1M tokens
-	"chatgpt-4o-latest":               2.5,  // $5 / 1M tokens
-	"gpt-4o":                          1.25, // $2.5 / 1M tokens
-	"gpt-4o-audio-preview":            1.25, // $2.5 / 1M tokens
-	"gpt-4o-audio-preview-2024-10-01": 1.25, // $2.5 / 1M tokens
-	"gpt-4o-2024-05-13":               2.5,  // $5 / 1M tokens
-	"gpt-4o-2024-08-06":               1.25, // $2.5 / 1M tokens
-	"gpt-4o-2024-11-20":               1.25, // $2.5 / 1M tokens
-	"gpt-4o-realtime-preview":         2.5,
-	"o1":                              7.5,
-	"o1-2024-12-17":                   7.5,
-	"o1-preview":                      7.5,
-	"o1-preview-2024-09-12":           7.5,
-	"o1-mini":                         1.5,
-	"o1-mini-2024-09-12":              1.5,
-	"gpt-4o-mini":                     0.075,
-	"gpt-4o-mini-2024-07-18":          0.075,
-	"gpt-4-turbo":                     5, // $0.01 / 1K tokens
-	"gpt-4-turbo-2024-04-09":          5, // $0.01 / 1K tokens
+	"gpt-4-32k-0613":                          30,
+	"gpt-4-1106-preview":                      5,    // $10 / 1M tokens
+	"gpt-4-0125-preview":                      5,    // $10 / 1M tokens
+	"gpt-4-turbo-preview":                     5,    // $10 / 1M tokens
+	"gpt-4-vision-preview":                    5,    // $10 / 1M tokens
+	"gpt-4-1106-vision-preview":               5,    // $10 / 1M tokens
+	"chatgpt-4o-latest":                       2.5,  // $5 / 1M tokens
+	"gpt-4o":                                  1.25, // $2.5 / 1M tokens
+	"gpt-4o-audio-preview":                    1.25, // $2.5 / 1M tokens
+	"gpt-4o-audio-preview-2024-10-01":         1.25, // $2.5 / 1M tokens
+	"gpt-4o-2024-05-13":                       2.5,  // $5 / 1M tokens
+	"gpt-4o-2024-08-06":                       1.25, // $2.5 / 1M tokens
+	"gpt-4o-2024-11-20":                       1.25, // $2.5 / 1M tokens
+	"gpt-4o-realtime-preview":                 2.5,
+	"gpt-4o-realtime-preview-2024-10-01":      2.5,
+	"gpt-4o-realtime-preview-2024-12-17":      2.5,
+	"gpt-4o-mini-realtime-preview":            0.3,
+	"gpt-4o-mini-realtime-preview-2024-12-17": 0.3,
+	"o1":                     7.5,
+	"o1-2024-12-17":          7.5,
+	"o1-preview":             7.5,
+	"o1-preview-2024-09-12":  7.5,
+	"o1-mini":                1.5,
+	"o1-mini-2024-09-12":     1.5,
+	"gpt-4o-mini":            0.075,
+	"gpt-4o-mini-2024-07-18": 0.075,
+	"gpt-4-turbo":            5, // $0.01 / 1K tokens
+	"gpt-4-turbo-2024-04-09": 5, // $0.01 / 1K tokens
 	//"gpt-3.5-turbo-0301":           0.75, //deprecated
 	"gpt-3.5-turbo":          0.25,
 	"gpt-3.5-turbo-0613":     0.75,
@@ -397,10 +401,13 @@ func GetCompletionRatio(name string) float64 {
 		case "command-r-plus-08-2024":
 			return 4
 		default:
-			return 2
+			return 4
 		}
 	}
 	if strings.HasPrefix(name, "deepseek") {
+		if name == "deepseek-reasoner" {
+			return 4
+		}
 		return 2
 	}
 	if strings.HasPrefix(name, "ERNIE-Speed-") {
@@ -427,10 +434,23 @@ func GetCompletionRatio(name string) float64 {
 }
 
 func GetAudioRatio(name string) float64 {
-	if strings.HasPrefix(name, "gpt-4o-realtime") {
-		return 20
-	} else if strings.HasPrefix(name, "gpt-4o-audio") {
-		return 40
+	if strings.Contains(name, "-realtime") {
+		if strings.HasSuffix(name, "gpt-4o-realtime-preview-2024-12-17") {
+			return 8
+		} else if strings.Contains(name, "mini") {
+			return 10 / 0.6
+		} else {
+			return 20
+		}
+	}
+	if strings.Contains(name, "-audio") {
+		if strings.HasSuffix(name, "gpt-4o-audio-preview-2024-12-17") {
+			return 16
+		} else if strings.Contains(name, "mini") {
+			return 10 / 0.15
+		} else {
+			return 40
+		}
 	}
 	return 20
 }
@@ -438,6 +458,8 @@ func GetAudioRatio(name string) float64 {
 func GetAudioCompletionRatio(name string) float64 {
 	if strings.HasPrefix(name, "gpt-4o-realtime") {
 		return 2
+	} else if strings.HasPrefix(name, "gpt-4o-mini-realtime") {
+		return 2
 	}
 	return 2
 }

common/utils.go

@@ -1,14 +1,19 @@
 package common
 
 import (
+	"bytes"
+	"context"
 	crand "crypto/rand"
 	"encoding/base64"
 	"fmt"
+	"github.com/pkg/errors"
 	"html/template"
+	"io"
 	"log"
 	"math/big"
 	"math/rand"
 	"net"
+	"os"
 	"os/exec"
 	"runtime"
 	"strconv"
@@ -207,3 +212,31 @@ func RandomSleep() {
 	// Sleep for 0-3000 ms
 	time.Sleep(time.Duration(rand.Intn(3000)) * time.Millisecond)
 }
+
+// SaveTmpFile saves data to a temporary file. The filename would be apppended with a random string.
+func SaveTmpFile(filename string, data io.Reader) (string, error) {
+	f, err := os.CreateTemp(os.TempDir(), filename)
+	if err != nil {
+		return "", errors.Wrapf(err, "failed to create temporary file %s", filename)
+	}
+	defer f.Close()
+
+	_, err = io.Copy(f, data)
+	if err != nil {
+		return "", errors.Wrapf(err, "failed to copy data to temporary file %s", filename)
+	}
+
+	return f.Name(), nil
+}
+
+// GetAudioDuration returns the duration of an audio file in seconds.
+func GetAudioDuration(ctx context.Context, filename string) (float64, error) {
+	// ffprobe -v error -show_entries format=duration -of default=noprint_wrappers=1:nokey=1 {{input}}
+	c := exec.CommandContext(ctx, "ffprobe", "-v", "error", "-show_entries", "format=duration", "-of", "default=noprint_wrappers=1:nokey=1", filename)
+	output, err := c.Output()
+	if err != nil {
+		return 0, errors.Wrap(err, "failed to get audio duration")
+	}
+
+	return strconv.ParseFloat(string(bytes.TrimSpace(output)), 64)
+}

controller/channel.go

@@ -274,6 +274,17 @@ func AddChannel(c *gin.Context) {
 		}
 		localChannel := channel
 		localChannel.Key = key
+		// Validate the length of the model name
+		models := strings.Split(localChannel.Models, ",")
+		for _, model := range models {
+			if len(model) > 255 {
+				c.JSON(http.StatusOK, gin.H{
+					"success": false,
+					"message": fmt.Sprintf("模型名称过长: %s", model),
+				})
+				return
+			}
+		}
 		channels = append(channels, localChannel)
 	}
 	err = model.BatchInsertChannels(channels)

docs/api/api_auth.md

@@ -0,0 +1,53 @@
+# API 鉴权文档
+
+## 认证方式
+
+### Access Token
+
+对于需要鉴权的 API 接口，必须同时提供以下两个请求头来进行 Access Token 认证：
+
+1. **请求头中的 `Authorization` 字段**
+
+    将 Access Token 放置于 HTTP 请求头部的 `Authorization` 字段中，格式如下：
+
+    ```
+    Authorization: <your_access_token>
+    ```
+
+    其中 `<your_access_token>` 需要替换为实际的 Access Token 值。
+
+2. **请求头中的 `New-Api-User` 字段**
+
+    将用户 ID 放置于 HTTP 请求头部的 `New-Api-User` 字段中，格式如下：
+
+    ```
+    New-Api-User: <your_user_id>
+    ```
+
+    其中 `<your_user_id>` 需要替换为实际的用户 ID。
+
+**注意：**
+
+*   **必须同时提供 `Authorization` 和 `New-Api-User` 两个请求头才能通过鉴权。**
+*   如果只提供其中一个请求头，或者两个请求头都未提供，则会返回 `401 Unauthorized` 错误。
+*   如果 `Authorization` 中的 Access Token 无效，则会返回 `401 Unauthorized` 错误，并提示“无权进行此操作，access token 无效”。
+*   如果 `New-Api-User` 中的用户 ID 与 Access Token 不匹配，则会返回 `401 Unauthorized` 错误，并提示“无权进行此操作，与登录用户不匹配，请重新登录”。
+*   如果没有提供 `New-Api-User` 请求头，则会返回 `401 Unauthorized` 错误，并提示“无权进行此操作，未提供 New-Api-User”。
+*   如果 `New-Api-User` 请求头格式错误，则会返回 `401 Unauthorized` 错误，并提示“无权进行此操作，New-Api-User 格式错误”。
+*   如果用户已被禁用，则会返回 `403 Forbidden` 错误，并提示“用户已被封禁”。
+*   如果用户权限不足，则会返回 `403 Forbidden` 错误，并提示“无权进行此操作，权限不足”。
+*   如果用户信息无效，则会返回 `403 Forbidden` 错误，并提示“无权进行此操作，用户信息无效”。
+
+## Curl 示例
+
+假设您的 Access Token 为 `access_token`，用户 ID 为 `123`，要访问的 API 接口为 `/api/user/self`，则可以使用以下 curl 命令：
+
+```bash
+curl -X GET \
+  -H "Authorization: access_token" \
+  -H "New-Api-User: 123" \
+  https://your-domain.com/api/user/self
+```
+
+请将 `access_token`、`123` 和 `https://your-domain.com` 替换为实际的值。
+

middleware/auth.go

@@ -64,35 +64,33 @@ func authHelper(c *gin.Context, minRole int) {
 			return
 		}
 	}
-	if !useAccessToken {
-		// get header New-Api-User
-		apiUserIdStr := c.Request.Header.Get("New-Api-User")
-		if apiUserIdStr == "" {
-			c.JSON(http.StatusUnauthorized, gin.H{
-				"success": false,
-				"message": "无权进行此操作，请刷新页面或清空缓存后重试",
-			})
-			c.Abort()
-			return
-		}
-		apiUserId, err := strconv.Atoi(apiUserIdStr)
-		if err != nil {
-			c.JSON(http.StatusUnauthorized, gin.H{
-				"success": false,
-				"message": "无权进行此操作，登录信息无效，请重新登录",
-			})
-			c.Abort()
-			return
+	// get header New-Api-User
+	apiUserIdStr := c.Request.Header.Get("New-Api-User")
+	if apiUserIdStr == "" {
+		c.JSON(http.StatusUnauthorized, gin.H{
+			"success": false,
+			"message": "无权进行此操作，未提供 New-Api-User",
+		})
+		c.Abort()
+		return
+	}
+	apiUserId, err := strconv.Atoi(apiUserIdStr)
+	if err != nil {
+		c.JSON(http.StatusUnauthorized, gin.H{
+			"success": false,
+			"message": "无权进行此操作，New-Api-User 格式错误",
+		})
+		c.Abort()
+		return
 
-		}
-		if id != apiUserId {
-			c.JSON(http.StatusUnauthorized, gin.H{
-				"success": false,
-				"message": "无权进行此操作，与登录用户不匹配，请重新登录",
-			})
-			c.Abort()
-			return
-		}
+	}
+	if id != apiUserId {
+		c.JSON(http.StatusUnauthorized, gin.H{
+			"success": false,
+			"message": "无权进行此操作，New-Api-User 与登录用户不匹配",
+		})
+		c.Abort()
+		return
 	}
 	if status.(int) == common.UserStatusDisabled {
 		c.JSON(http.StatusOK, gin.H{

model/ability.go

@@ -12,7 +12,7 @@ import (
 
 type Ability struct {
 	Group     string  `json:"group" gorm:"type:varchar(64);primaryKey;autoIncrement:false"`
-	Model     string  `json:"model" gorm:"type:varchar(64);primaryKey;autoIncrement:false"`
+	Model     string  `json:"model" gorm:"type:varchar(255);primaryKey;autoIncrement:false"`
 	ChannelId int     `json:"channel_id" gorm:"primaryKey;autoIncrement:false;index"`
 	Enabled   bool    `json:"enabled"`
 	Priority  *int64  `json:"priority" gorm:"bigint;default:0;index"`
@@ -278,7 +278,6 @@ func FixAbility() (int, error) {
 		return 0, err
 	}
 	var channels []Channel
-
 	if len(abilityChannelIds) == 0 {
 		err = DB.Find(&channels).Error
 	} else {

model/log.go

@@ -27,6 +27,7 @@ type Log struct {
 	UseTime          int    `json:"use_time" gorm:"default:0"`
 	IsStream         bool   `json:"is_stream" gorm:"default:false"`
 	ChannelId        int    `json:"channel" gorm:"index"`
+	ChannelName      string `json:"channel_name" gorm:"->"`
 	TokenId          int    `json:"token_id" gorm:"default:0;index"`
 	Group            string `json:"group" gorm:"index"`
 	Other            string `json:"other"`
@@ -128,34 +129,38 @@ func GetAllLogs(logType int, startTimestamp int64, endTimestamp int64, modelName
 	if logType == LogTypeUnknown {
 		tx = LOG_DB
 	} else {
-		tx = LOG_DB.Where("type = ?", logType)
+		tx = LOG_DB.Where("logs.type = ?", logType)
 	}
+
+	tx = tx.Joins("LEFT JOIN channels ON logs.channel_id = channels.id")
+	tx = tx.Select("logs.*, channels.name as channel_name")
+
 	if modelName != "" {
-		tx = tx.Where("model_name like ?", modelName)
+		tx = tx.Where("logs.model_name like ?", modelName)
 	}
 	if username != "" {
-		tx = tx.Where("username = ?", username)
+		tx = tx.Where("logs.username = ?", username)
 	}
 	if tokenName != "" {
-		tx = tx.Where("token_name = ?", tokenName)
+		tx = tx.Where("logs.token_name = ?", tokenName)
 	}
 	if startTimestamp != 0 {
-		tx = tx.Where("created_at >= ?", startTimestamp)
+		tx = tx.Where("logs.created_at >= ?", startTimestamp)
 	}
 	if endTimestamp != 0 {
-		tx = tx.Where("created_at <= ?", endTimestamp)
+		tx = tx.Where("logs.created_at <= ?", endTimestamp)
 	}
 	if channel != 0 {
-		tx = tx.Where("channel_id = ?", channel)
+		tx = tx.Where("logs.channel_id = ?", channel)
 	}
 	if group != "" {
-		tx = tx.Where(groupCol+" = ?", group)
+		tx = tx.Where("logs."+groupCol+" = ?", group)
 	}
 	err = tx.Model(&Log{}).Count(&total).Error
 	if err != nil {
 		return nil, 0, err
 	}
-	err = tx.Order("id desc").Limit(num).Offset(startIdx).Find(&logs).Error
+	err = tx.Order("logs.id desc").Limit(num).Offset(startIdx).Find(&logs).Error
 	if err != nil {
 		return nil, 0, err
 	}
@@ -165,30 +170,34 @@ func GetAllLogs(logType int, startTimestamp int64, endTimestamp int64, modelName
 func GetUserLogs(userId int, logType int, startTimestamp int64, endTimestamp int64, modelName string, tokenName string, startIdx int, num int, group string) (logs []*Log, total int64, err error) {
 	var tx *gorm.DB
 	if logType == LogTypeUnknown {
-		tx = LOG_DB.Where("user_id = ?", userId)
+		tx = LOG_DB.Where("logs.user_id = ?", userId)
 	} else {
-		tx = LOG_DB.Where("user_id = ? and type = ?", userId, logType)
+		tx = LOG_DB.Where("logs.user_id = ? and logs.type = ?", userId, logType)
 	}
+
+	tx = tx.Joins("LEFT JOIN channels ON logs.channel_id = channels.id")
+	tx = tx.Select("logs.*, channels.name as channel_name")
+
 	if modelName != "" {
-		tx = tx.Where("model_name like ?", modelName)
+		tx = tx.Where("logs.model_name like ?", modelName)
 	}
 	if tokenName != "" {
-		tx = tx.Where("token_name = ?", tokenName)
+		tx = tx.Where("logs.token_name = ?", tokenName)
 	}
 	if startTimestamp != 0 {
-		tx = tx.Where("created_at >= ?", startTimestamp)
+		tx = tx.Where("logs.created_at >= ?", startTimestamp)
 	}
 	if endTimestamp != 0 {
-		tx = tx.Where("created_at <= ?", endTimestamp)
+		tx = tx.Where("logs.created_at <= ?", endTimestamp)
 	}
 	if group != "" {
-		tx = tx.Where(groupCol+" = ?", group)
+		tx = tx.Where("logs."+groupCol+" = ?", group)
 	}
 	err = tx.Model(&Log{}).Count(&total).Error
 	if err != nil {
 		return nil, 0, err
 	}
-	err = tx.Order("id desc").Limit(num).Offset(startIdx).Find(&logs).Error
+	err = tx.Order("logs.id desc").Limit(num).Offset(startIdx).Find(&logs).Error
 	formatUserLogs(logs)
 	return logs, total, err
 }

model/user.go

@@ -134,18 +134,23 @@ func SearchUsers(keyword string, group string, startIdx int, num int) ([]*User,
 	// 构建基础查询
 	query := tx.Unscoped().Model(&User{})
 
+	// 构建搜索条件
+	likeCondition := "username LIKE ? OR email LIKE ? OR display_name LIKE ?"
+
 	// 尝试将关键字转换为整数ID
 	keywordInt, err := strconv.Atoi(keyword)
 	if err == nil {
-		// 如果转换成功，按照ID和可选的组别搜索用户
+		// 如果是数字，同时搜索ID和其他字段
+		likeCondition = "id = ? OR " + likeCondition
 		if group != "" {
-			query = query.Where("id = ? AND "+groupCol+" = ?", keywordInt, group)
+			query = query.Where("("+likeCondition+") AND "+groupCol+" = ?",
+				keywordInt, "%"+keyword+"%", "%"+keyword+"%", "%"+keyword+"%", group)
 		} else {
-			query = query.Where("id = ?", keywordInt)
+			query = query.Where(likeCondition,
+				keywordInt, "%"+keyword+"%", "%"+keyword+"%", "%"+keyword+"%")
 		}
 	} else {
-		// 如果不是ID搜索，则使用模糊匹配
-		likeCondition := "username LIKE ? OR email LIKE ? OR display_name LIKE ?"
+		// 非数字关键字，只搜索字符串字段
 		if group != "" {
 			query = query.Where("("+likeCondition+") AND "+groupCol+" = ?",
 				"%"+keyword+"%", "%"+keyword+"%", "%"+keyword+"%", group)

relay/channel/deepseek/constants.go

@@ -1,7 +1,7 @@
 package deepseek
 
 var ModelList = []string{
-	"deepseek-chat", "deepseek-coder",
+	"deepseek-chat", "deepseek-reasoner",
 }
 
 var ChannelName = "deepseek"

relay/channel/openai/constant.go

@@ -15,7 +15,8 @@ var ModelList = []string{
 	"o1-mini", "o1-mini-2024-09-12",
 	"o1", "o1-2024-12-17",
 	"gpt-4o-audio-preview", "gpt-4o-audio-preview-2024-10-01",
-	"gpt-4o-realtime-preview", "gpt-4o-realtime-preview-2024-10-01",
+	"gpt-4o-realtime-preview", "gpt-4o-realtime-preview-2024-10-01", "gpt-4o-realtime-preview-2024-12-17",
+	"gpt-4o-mini-realtime-preview", "gpt-4o-mini-realtime-preview-2024-12-17",
 	"text-embedding-ada-002", "text-embedding-3-small", "text-embedding-3-large",
 	"text-curie-001", "text-babbage-001", "text-ada-001",
 	"text-moderation-latest", "text-moderation-stable",

relay/channel/openai/relay-openai.go

@@ -5,7 +5,10 @@ import (
 	"bytes"
 	"encoding/json"
 	"fmt"
+	"github.com/pkg/errors"
 	"io"
+	"math"
+	"mime/multipart"
 	"net/http"
 	"one-api/common"
 	"one-api/constant"
@@ -13,6 +16,7 @@ import (
 	relaycommon "one-api/relay/common"
 	relayconstant "one-api/relay/constant"
 	"one-api/service"
+	"os"
 	"strings"
 	"sync"
 	"time"
@@ -65,8 +69,12 @@ func OaiStreamHandler(c *gin.Context, resp *http.Response, info *relaycommon.Rel
 	scanner.Split(bufio.ScanLines)
 
 	service.SetEventStreamHeaders(c)
-
-	ticker := time.NewTicker(time.Duration(constant.StreamingTimeout) * time.Second)
+	streamingTimeout := time.Duration(constant.StreamingTimeout) * time.Second
+	if strings.HasPrefix(info.UpstreamModelName, "o1") || strings.HasPrefix(info.UpstreamModelName, "o3") {
+		// twice timeout for o1 model
+		streamingTimeout *= 2
+	}
+	ticker := time.NewTicker(streamingTimeout)
 	defer ticker.Stop()
 
 	stopChan := make(chan bool)
@@ -312,6 +320,11 @@ func OpenaiTTSHandler(c *gin.Context, resp *http.Response, info *relaycommon.Rel
 }
 
 func OpenaiSTTHandler(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo, responseFormat string) (*dto.OpenAIErrorWithStatusCode, *dto.Usage) {
+	// count tokens by audio file duration
+	audioTokens, err := countAudioTokens(c)
+	if err != nil {
+		return service.OpenAIErrorWrapper(err, "count_audio_tokens_failed", http.StatusInternalServerError), nil
+	}
 	responseBody, err := io.ReadAll(resp.Body)
 	if err != nil {
 		return service.OpenAIErrorWrapper(err, "read_response_body_failed", http.StatusInternalServerError), nil
@@ -336,70 +349,52 @@ func OpenaiSTTHandler(c *gin.Context, resp *http.Response, info *relaycommon.Rel
 	}
 	resp.Body.Close()
 
-	var text string
-	switch responseFormat {
-	case "json":
-		text, err = getTextFromJSON(responseBody)
-	case "text":
-		text, err = getTextFromText(responseBody)
-	case "srt":
-		text, err = getTextFromSRT(responseBody)
-	case "verbose_json":
-		text, err = getTextFromVerboseJSON(responseBody)
-	case "vtt":
-		text, err = getTextFromVTT(responseBody)
-	}
-
 	usage := &dto.Usage{}
-	usage.PromptTokens = info.PromptTokens
-	usage.CompletionTokens, _ = service.CountTextToken(text, info.UpstreamModelName)
+	usage.PromptTokens = audioTokens
+	usage.CompletionTokens = 0
 	usage.TotalTokens = usage.PromptTokens + usage.CompletionTokens
 	return nil, usage
 }
 
-func getTextFromVTT(body []byte) (string, error) {
-	return getTextFromSRT(body)
-}
-
-func getTextFromVerboseJSON(body []byte) (string, error) {
-	var whisperResponse dto.WhisperVerboseJSONResponse
-	if err := json.Unmarshal(body, &whisperResponse); err != nil {
-		return "", fmt.Errorf("unmarshal_response_body_failed err :%w", err)
+func countAudioTokens(c *gin.Context) (int, error) {
+	body, err := common.GetRequestBody(c)
+	if err != nil {
+		return 0, errors.WithStack(err)
 	}
-	return whisperResponse.Text, nil
-}
 
-func getTextFromSRT(body []byte) (string, error) {
-	scanner := bufio.NewScanner(strings.NewReader(string(body)))
-	var builder strings.Builder
-	var textLine bool
-	for scanner.Scan() {
-		line := scanner.Text()
-		if textLine {
-			builder.WriteString(line)
-			textLine = false
-			continue
-		} else if strings.Contains(line, "-->") {
-			textLine = true
-			continue
-		}
+	var reqBody struct {
+		File *multipart.FileHeader `form:"file" binding:"required"`
 	}
-	if err := scanner.Err(); err != nil {
-		return "", err
+	c.Request.Body = io.NopCloser(bytes.NewReader(body))
+	if err = c.ShouldBind(&reqBody); err != nil {
+		return 0, errors.WithStack(err)
 	}
-	return builder.String(), nil
-}
 
-func getTextFromText(body []byte) (string, error) {
-	return strings.TrimSuffix(string(body), "\n"), nil
-}
-
-func getTextFromJSON(body []byte) (string, error) {
-	var whisperResponse dto.AudioResponse
-	if err := json.Unmarshal(body, &whisperResponse); err != nil {
-		return "", fmt.Errorf("unmarshal_response_body_failed err :%w", err)
+	reqFp, err := reqBody.File.Open()
+	if err != nil {
+		return 0, errors.WithStack(err)
 	}
-	return whisperResponse.Text, nil
+
+	tmpFp, err := os.CreateTemp("", "audio-*")
+	if err != nil {
+		return 0, errors.WithStack(err)
+	}
+	defer os.Remove(tmpFp.Name())
+
+	_, err = io.Copy(tmpFp, reqFp)
+	if err != nil {
+		return 0, errors.WithStack(err)
+	}
+	if err = tmpFp.Close(); err != nil {
+		return 0, errors.WithStack(err)
+	}
+
+	duration, err := common.GetAudioDuration(c.Request.Context(), tmpFp.Name())
+	if err != nil {
+		return 0, errors.WithStack(err)
+	}
+
+	return int(math.Round(math.Ceil(duration) / 60.0 * 1000)), nil // 1 minute 相当于 1k tokens
 }
 
 func OpenaiRealtimeHandler(c *gin.Context, info *relaycommon.RelayInfo) (*dto.OpenAIErrorWithStatusCode, *dto.RealtimeUsage) {

relay/relay-text.go

@@ -112,6 +112,7 @@ func TextHelper(c *gin.Context) (openaiErr *dto.OpenAIErrorWithStatusCode) {
 	var promptTokens int
 	if value, exists := c.Get("prompt_tokens"); exists {
 		promptTokens = value.(int)
+		relayInfo.PromptTokens = promptTokens
 	} else {
 		promptTokens, err = getPromptTokens(textRequest, relayInfo)
 		// count messages token error 计算promptTokens错误
@@ -218,7 +219,7 @@ func TextHelper(c *gin.Context) (openaiErr *dto.OpenAIErrorWithStatusCode) {
 	}
 
 	if strings.HasPrefix(relayInfo.UpstreamModelName, "gpt-4o-audio") {
-		service.PostAudioConsumeQuota(c, relayInfo, usage.(*dto.Usage), ratio, preConsumedQuota, userQuota, modelRatio, groupRatio, modelPrice, getModelPriceSuccess, "")
+		service.PostAudioConsumeQuota(c, relayInfo, usage.(*dto.Usage), preConsumedQuota, userQuota, modelRatio, groupRatio, modelPrice, getModelPriceSuccess, "")
 	} else {
 		postConsumeQuota(c, relayInfo, textRequest.Model, usage.(*dto.Usage), ratio, preConsumedQuota, userQuota, modelRatio, groupRatio, modelPrice, getModelPriceSuccess, "")
 	}

relay/websocket.go

@@ -13,24 +13,6 @@ import (
 	"one-api/setting"
 )
 
-//func getAndValidateWssRequest(c *gin.Context, ws *websocket.Conn) (*dto.RealtimeEvent, error) {
-//	_, p, err := ws.ReadMessage()
-//	if err != nil {
-//		return nil, err
-//	}
-//	realtimeEvent := &dto.RealtimeEvent{}
-//	err = json.Unmarshal(p, realtimeEvent)
-//	if err != nil {
-//		return nil, err
-//	}
-//	// save the original request
-//	if realtimeEvent.Session == nil {
-//		return nil, errors.New("session object is nil")
-//	}
-//	c.Set("first_wss_request", p)
-//	return realtimeEvent, nil
-//}
-
 func WssHelper(c *gin.Context, ws *websocket.Conn) (openaiErr *dto.OpenAIErrorWithStatusCode) {
 	relayInfo := relaycommon.GenRelayInfoWs(c, ws)
 
@@ -129,32 +111,7 @@ func WssHelper(c *gin.Context, ws *websocket.Conn) (openaiErr *dto.OpenAIErrorWi
 		service.ResetStatusCode(openaiErr, statusCodeMappingStr)
 		return openaiErr
 	}
-	service.PostWssConsumeQuota(c, relayInfo, relayInfo.UpstreamModelName, usage.(*dto.RealtimeUsage), ratio, preConsumedQuota, userQuota, modelRatio, groupRatio, modelPrice, getModelPriceSuccess, "")
+	service.PostWssConsumeQuota(c, relayInfo, relayInfo.UpstreamModelName, usage.(*dto.RealtimeUsage), preConsumedQuota,
+		userQuota, modelRatio, groupRatio, modelPrice, getModelPriceSuccess, "")
 	return nil
 }
-
-//func getWssPromptTokens(textRequest *dto.RealtimeEvent, info *relaycommon.RelayInfo) (int, error) {
-//	var promptTokens int
-//	var err error
-//	switch info.RelayMode {
-//	default:
-//		promptTokens, err = service.CountTokenRealtime(*textRequest, info.UpstreamModelName)
-//	}
-//	info.PromptTokens = promptTokens
-//	return promptTokens, err
-//}
-
-//func checkWssRequestSensitive(textRequest *dto.GeneralOpenAIRequest, info *relaycommon.RelayInfo) error {
-//	var err error
-//	switch info.RelayMode {
-//	case relayconstant.RelayModeChatCompletions:
-//		err = service.CheckSensitiveMessages(textRequest.Messages)
-//	case relayconstant.RelayModeCompletions:
-//		err = service.CheckSensitiveInput(textRequest.Prompt)
-//	case relayconstant.RelayModeModerations:
-//		err = service.CheckSensitiveInput(textRequest.Input)
-//	case relayconstant.RelayModeEmbeddings:
-//		err = service.CheckSensitiveInput(textRequest.Input)
-//	}
-//	return err
-//}

service/quota.go

@@ -3,7 +3,6 @@ package service
 import (
 	"errors"
 	"fmt"
-	"github.com/gin-gonic/gin"
 	"math"
 	"one-api/common"
 	"one-api/dto"
@@ -12,8 +11,47 @@ import (
 	"one-api/setting"
 	"strings"
 	"time"
+
+	"github.com/gin-gonic/gin"
 )
 
+type TokenDetails struct {
+	TextTokens  int
+	AudioTokens int
+}
+
+type QuotaInfo struct {
+	InputDetails  TokenDetails
+	OutputDetails TokenDetails
+	ModelName     string
+	UsePrice      bool
+	ModelPrice    float64
+	ModelRatio    float64
+	GroupRatio    float64
+}
+
+func calculateAudioQuota(info QuotaInfo) int {
+	if info.UsePrice {
+		return int(info.ModelPrice * common.QuotaPerUnit * info.GroupRatio)
+	}
+
+	completionRatio := common.GetCompletionRatio(info.ModelName)
+	audioRatio := common.GetAudioRatio(info.ModelName)
+	audioCompletionRatio := common.GetAudioCompletionRatio(info.ModelName)
+	ratio := info.GroupRatio * info.ModelRatio
+
+	quota := info.InputDetails.TextTokens + int(math.Round(float64(info.OutputDetails.TextTokens)*completionRatio))
+	quota += int(math.Round(float64(info.InputDetails.AudioTokens)*audioRatio)) +
+		int(math.Round(float64(info.OutputDetails.AudioTokens)*audioRatio*audioCompletionRatio))
+
+	quota = int(math.Round(float64(quota) * ratio))
+	if ratio != 0 && quota <= 0 {
+		quota = 1
+	}
+
+	return quota
+}
+
 func PreWssConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo, usage *dto.RealtimeUsage) error {
 	if relayInfo.UsePrice {
 		return nil
@@ -33,23 +71,26 @@ func PreWssConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo, usag
 	textOutTokens := usage.OutputTokenDetails.TextTokens
 	audioInputTokens := usage.InputTokenDetails.AudioTokens
 	audioOutTokens := usage.OutputTokenDetails.AudioTokens
-
-	completionRatio := common.GetCompletionRatio(modelName)
-	audioRatio := common.GetAudioRatio(relayInfo.UpstreamModelName)
-	audioCompletionRatio := common.GetAudioCompletionRatio(modelName)
 	groupRatio := setting.GetGroupRatio(relayInfo.Group)
 	modelRatio := common.GetModelRatio(modelName)
 
-	ratio := groupRatio * modelRatio
-
-	quota := textInputTokens + int(math.Round(float64(textOutTokens)*completionRatio))
-	quota += int(math.Round(float64(audioInputTokens)*audioRatio)) + int(math.Round(float64(audioOutTokens)*audioRatio*audioCompletionRatio))
-
-	quota = int(math.Round(float64(quota) * ratio))
-	if ratio != 0 && quota <= 0 {
-		quota = 1
+	quotaInfo := QuotaInfo{
+		InputDetails: TokenDetails{
+			TextTokens:  textInputTokens,
+			AudioTokens: audioInputTokens,
+		},
+		OutputDetails: TokenDetails{
+			TextTokens:  textOutTokens,
+			AudioTokens: audioOutTokens,
+		},
+		ModelName:  modelName,
+		UsePrice:   relayInfo.UsePrice,
+		ModelRatio: modelRatio,
+		GroupRatio: groupRatio,
 	}
 
+	quota := calculateAudioQuota(quotaInfo)
+
 	if userQuota < quota {
 		return errors.New(fmt.Sprintf("用户额度不足，剩余额度为 %d", userQuota))
 	}
@@ -67,8 +108,7 @@ func PreWssConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo, usag
 }
 
 func PostWssConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo, modelName string,
-	usage *dto.RealtimeUsage, ratio float64, preConsumedQuota int, userQuota int, modelRatio float64,
-	groupRatio float64,
+	usage *dto.RealtimeUsage, preConsumedQuota int, userQuota int, modelRatio float64, groupRatio float64,
 	modelPrice float64, usePrice bool, extraContent string) {
 
 	useTimeSeconds := time.Now().Unix() - relayInfo.StartTime.Unix()
@@ -83,17 +123,23 @@ func PostWssConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo, mod
 	audioRatio := common.GetAudioRatio(relayInfo.UpstreamModelName)
 	audioCompletionRatio := common.GetAudioCompletionRatio(modelName)
 
-	quota := 0
-	if !usePrice {
-		quota = int(math.Round(float64(textInputTokens) + float64(textOutTokens)*completionRatio))
-		quota += int(math.Round(float64(audioInputTokens)*audioRatio + float64(audioOutTokens)*audioRatio*audioCompletionRatio))
-		quota = int(math.Round(float64(quota) * ratio))
-		if ratio != 0 && quota <= 0 {
-			quota = 1
-		}
-	} else {
-		quota = int(modelPrice * common.QuotaPerUnit * groupRatio)
+	quotaInfo := QuotaInfo{
+		InputDetails: TokenDetails{
+			TextTokens:  textInputTokens,
+			AudioTokens: audioInputTokens,
+		},
+		OutputDetails: TokenDetails{
+			TextTokens:  textOutTokens,
+			AudioTokens: audioOutTokens,
+		},
+		ModelName:  modelName,
+		UsePrice:   usePrice,
+		ModelRatio: modelRatio,
+		GroupRatio: groupRatio,
 	}
+
+	quota := calculateAudioQuota(quotaInfo)
+
 	totalTokens := usage.TotalTokens
 	var logContent string
 	if !usePrice {
@@ -111,21 +157,6 @@ func PostWssConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo, mod
 		common.LogError(ctx, fmt.Sprintf("total tokens is 0, cannot consume quota, userId %d, channelId %d, "+
 			"tokenId %d, model %s， pre-consumed quota %d", relayInfo.UserId, relayInfo.ChannelId, relayInfo.TokenId, modelName, preConsumedQuota))
 	} else {
-		//if sensitiveResp != nil {
-		//	logContent += fmt.Sprintf("，敏感词：%s", strings.Join(sensitiveResp.SensitiveWords, ", "))
-		//}
-		//quotaDelta := quota - preConsumedQuota
-		//if quotaDelta != 0 {
-		//	err := model.PostConsumeQuota(relayInfo, userQuota, quotaDelta, preConsumedQuota, true)
-		//	if err != nil {
-		//		common.LogError(ctx, "error consuming token remain quota: "+err.Error())
-		//	}
-		//}
-
-		//err := model.CacheUpdateUserQuota(relayInfo.UserId)
-		//if err != nil {
-		//	common.LogError(ctx, "error update user quota cache: "+err.Error())
-		//}
 		model.UpdateUserUsedQuotaAndRequestCount(relayInfo.UserId, quota)
 		model.UpdateChannelUsedQuota(relayInfo.ChannelId, quota)
 	}
@@ -140,8 +171,7 @@ func PostWssConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo, mod
 }
 
 func PostAudioConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo,
-	usage *dto.Usage, ratio float64, preConsumedQuota int, userQuota int, modelRatio float64,
-	groupRatio float64,
+	usage *dto.Usage, preConsumedQuota int, userQuota int, modelRatio float64, groupRatio float64,
 	modelPrice float64, usePrice bool, extraContent string) {
 
 	useTimeSeconds := time.Now().Unix() - relayInfo.StartTime.Unix()
@@ -156,17 +186,23 @@ func PostAudioConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo,
 	audioRatio := common.GetAudioRatio(relayInfo.UpstreamModelName)
 	audioCompletionRatio := common.GetAudioCompletionRatio(relayInfo.UpstreamModelName)
 
-	quota := 0
-	if !usePrice {
-		quota = int(math.Round(float64(textInputTokens) + float64(textOutTokens)*completionRatio))
-		quota += int(math.Round(float64(audioInputTokens)*audioRatio + float64(audioOutTokens)*audioRatio*audioCompletionRatio))
-		quota = int(math.Round(float64(quota) * ratio))
-		if ratio != 0 && quota <= 0 {
-			quota = 1
-		}
-	} else {
-		quota = int(modelPrice * common.QuotaPerUnit * groupRatio)
+	quotaInfo := QuotaInfo{
+		InputDetails: TokenDetails{
+			TextTokens:  textInputTokens,
+			AudioTokens: audioInputTokens,
+		},
+		OutputDetails: TokenDetails{
+			TextTokens:  textOutTokens,
+			AudioTokens: audioOutTokens,
+		},
+		ModelName:  relayInfo.UpstreamModelName,
+		UsePrice:   usePrice,
+		ModelRatio: modelRatio,
+		GroupRatio: groupRatio,
 	}
+
+	quota := calculateAudioQuota(quotaInfo)
+
 	totalTokens := usage.TotalTokens
 	var logContent string
 	if !usePrice {

service/token_counter.go

@@ -92,13 +92,6 @@ func getImageToken(info *relaycommon.RelayInfo, imageUrl *dto.MessageImageUrl, m
 	if !constant.GetMediaTokenNotStream && !stream {
 		return 256, nil
 	}
-	// 是否统计图片token
-	if !constant.GetMediaToken {
-		return 256, nil
-	}
-	if info.ChannelType == common.ChannelTypeGemini || info.ChannelType == common.ChannelTypeVertexAi || info.ChannelType == common.ChannelTypeAnthropic {
-		return 256, nil
-	}
 	// 同步One API的图片计费逻辑
 	if imageUrl.Detail == "auto" || imageUrl.Detail == "" {
 		imageUrl.Detail = "high"
@@ -109,6 +102,13 @@ func getImageToken(info *relaycommon.RelayInfo, imageUrl *dto.MessageImageUrl, m
 		tileTokens = 5667
 		baseTokens = 2833
 	}
+	// 是否统计图片token
+	if !constant.GetMediaToken {
+		return 3 * baseTokens, nil
+	}
+	if info.ChannelType == common.ChannelTypeGemini || info.ChannelType == common.ChannelTypeVertexAi || info.ChannelType == common.ChannelTypeAnthropic {
+		return 3 * baseTokens, nil
+	}
 	var config image.Config
 	var err error
 	var format string

web/src/components/LogsTable.js

@@ -157,13 +157,15 @@ const LogsTable = () => {
           record.type === 0 || record.type === 2 ? (
             <div>
               {
-                <Tag
-                  color={colors[parseInt(text) % colors.length]}
-                  size='large'
-                >
-                  {' '}
-                  {text}{' '}
-                </Tag>
+                <Tooltip content={record.channel_name || '[未知]'}>
+                  <Tag
+                    color={colors[parseInt(text) % colors.length]}
+                    size='large'
+                  >
+                    {' '}
+                    {text}{' '}
+                  </Tag>
+                </Tooltip>
               }
             </div>
           ) : (
@@ -234,7 +236,12 @@ const LogsTable = () => {
               </>
             );
          } else {
-           let other = JSON.parse(record.other);
+           let other = null;
+           try {
+             other = JSON.parse(record.other);
+           } catch (e) {
+             console.error(`Failed to parse record.other: "${record.other}".`, e);
+           }
            if (other === null) {
              return <></>;
            }
@@ -543,6 +550,12 @@ const LogsTable = () => {
         //   key: '渠道重试',
         //   value: content,
         // })
+      }      
+      if (isAdminUser && (logs[i].type === 0 || logs[i].type === 2)) {
+        expandDataLocal.push({
+          key: t('渠道信息'),
+          value: `${logs[i].channel} - ${logs[i].channel_name || '[未知]'}`
+        });
       }
       if (other?.ws || other?.audio) {
         expandDataLocal.push({
@@ -595,13 +608,12 @@ const LogsTable = () => {
           key: t('计费过程'),
           value: content,
         });
-      }
 
+      }
       expandDatesLocal[logs[i].key] = expandDataLocal;
     }
 
     setExpandData(expandDatesLocal);
-
     setLogs(logs);
   };
 

web/src/helpers/render.js

@@ -315,6 +315,9 @@ export function renderAudioModelPrice(
     if (completionRatio === undefined) {
       completionRatio = 0;
     }
+
+    // try toFixed audioRatio
+    audioRatio = parseFloat(audioRatio).toFixed(6);
     // 这里的 *2 是因为 1倍率=0.002刀，请勿删除
     let inputRatioPrice = modelRatio * 2.0;
     let completionRatioPrice = modelRatio * 2.0 * completionRatio;
@@ -326,13 +329,31 @@ export function renderAudioModelPrice(
     return (
       <>
         <article>
-          <p>提示：${inputRatioPrice} * {groupRatio} = ${inputRatioPrice * groupRatio} / 1M tokens</p>
-          <p>补全：${completionRatioPrice} * {groupRatio} = ${completionRatioPrice * groupRatio} / 1M tokens</p>
-          <p>音频提示：${inputRatioPrice} * {groupRatio} * {audioRatio} = ${inputRatioPrice * audioRatio * groupRatio} / 1M tokens</p>
-          <p>音频补全：${inputRatioPrice} * {groupRatio} * {audioRatio} * {audioCompletionRatio} = ${inputRatioPrice * audioRatio * audioCompletionRatio * groupRatio} / 1M tokens</p>
-          <p></p>
+          <p>{i18next.t('提示：${{price}} * {{ratio}} = ${{total}} / 1M tokens', {
+            price: inputRatioPrice,
+            ratio: groupRatio,
+            total: inputRatioPrice * groupRatio
+          })}</p>
+          <p>{i18next.t('补全：${{price}} * {{ratio}} = ${{total}} / 1M tokens', {
+            price: completionRatioPrice,
+            ratio: groupRatio,
+            total: completionRatioPrice * groupRatio
+          })}</p>
+          <p>{i18next.t('音频提示：${{price}} * {{ratio}} * {{audioRatio}} = ${{total}} / 1M tokens', {
+            price: inputRatioPrice,
+            ratio: groupRatio,
+            audioRatio,
+            total: inputRatioPrice * audioRatio * groupRatio
+          })}</p>
+          <p>{i18next.t('音频补全：${{price}} * {{ratio}} * {{audioRatio}} * {{audioCompRatio}} = ${{total}} / 1M tokens', {
+            price: inputRatioPrice,
+            ratio: groupRatio,
+            audioRatio,
+            audioCompRatio: audioCompletionRatio,
+            total: inputRatioPrice * audioRatio * audioCompletionRatio * groupRatio
+          })}</p>
           <p>
-            {i18next.t('提示 {{input}} tokens / 1M tokens * ${{price}} + 补全 {{completion}} tokens / 1M tokens * ${{compPrice}} +', {
+            {i18next.t('文字提示 {{input}} tokens / 1M tokens * ${{price}} + 文字补全 {{completion}} tokens / 1M tokens * ${{compPrice}} +', {
               input: inputTokens,
               price: inputRatioPrice,
               completion: completionTokens,
@@ -340,13 +361,21 @@ export function renderAudioModelPrice(
             })}
           </p>
           <p>
-            音频提示 {audioInputTokens} tokens / 1M tokens * ${inputRatioPrice} * {audioRatio} + 音频补全 {audioCompletionTokens} tokens / 1M tokens * ${inputRatioPrice} * {audioRatio} * {audioCompletionRatio}
+            {i18next.t('音频提示 {{input}} tokens / 1M tokens * ${{price}} * {{audioRatio}} + 音频补全 {{completion}} tokens / 1M tokens * ${{price}} * {{audioRatio}} * {{audioCompRatio}}', {
+              input: audioInputTokens,
+              completion: audioCompletionTokens,
+              price: inputRatioPrice,
+              audioRatio,
+              audioCompRatio: audioCompletionRatio
+            })}
           </p>
           <p>
-            （文字 + 音频） * 分组 {groupRatio} =
-            ${price.toFixed(6)}
+            {i18next.t('（文字 + 音频）* 分组倍率 {{ratio}} = ${{total}}', {
+              ratio: groupRatio,
+              total: price.toFixed(6)
+            })}
           </p>
-          <p>仅供参考，以实际扣费为准</p>
+          <p>{i18next.t('仅供参考，以实际扣费为准')}</p>
         </article>
       </>
     );
@@ -377,13 +406,13 @@ const colors = [
   'red',
   'teal',
   'violet',
-  'yellow',
+  'yellow'
 ];
 
 // 基础10色色板 (N ≤ 10)
 const baseColors = [
   '#1664FF', // 主色
-  '#1AC6FF', 
+  '#1AC6FF',
   '#FF8A00',
   '#3CC780',
   '#7442D4',

web/src/i18n/locales/en.json

@@ -853,7 +853,7 @@
   "数量": "quantity",
   "请选择或输入创建令牌的数量": "Please select or enter the number of tokens to create",
   "请选择渠道": "Please select a channel",
-  "允许的IP，一行一个": "Allowed IPs, one per line",
+  "允许的IP，一行一个，不填写则不限制": "Allowed IPs, one per line, not filled in means no restrictions",
   "IP黑名单": "IP blacklist",
   "不允许的IP，一行一个": "IPs not allowed, one per line",
   "请选择该渠道所支持的模型": "Please select the model supported by this channel",
@@ -1053,6 +1053,11 @@
   "模型价格：${{price}} * 分组倍率：{{ratio}} = ${{total}}": "Model price: ${{price}} * Group ratio: {{ratio}} = ${{total}}",
   "提示：${{price}} * {{ratio}} = ${{total}} / 1M tokens": "Prompt: ${{price}} * {{ratio}} = ${{total}} / 1M tokens",
   "补全：${{price}} * {{ratio}} = ${{total}} / 1M tokens": "Completion: ${{price}} * {{ratio}} = ${{total}} / 1M tokens",
+  "音频提示：${{price}} * {{ratio}} * {{audioRatio}} = ${{total}} / 1M tokens": "Audio prompt: ${{price}} * {{ratio}} * {{audioRatio}} = ${{total}} / 1M tokens",
+  "音频提示 {{input}} tokens / 1M tokens * ${{price}} * {{audioRatio}} + 音频补全 {{completion}} tokens / 1M tokens * ${{price}} * {{audioRatio}} * {{audioCompRatio}}": "Audio prompt {{input}} tokens / 1M tokens * ${{price}} * {{audioRatio}} + Audio completion {{completion}} tokens / 1M tokens * ${{price}} * {{audioRatio}} * {{audioCompRatio}}",
+  "音频补全：${{price}} * {{ratio}} * {{audioRatio}} * {{audioCompRatio}} = ${{total}} / 1M tokens": "Audio completion: ${{price}} * {{ratio}} * {{audioRatio}} * {{audioCompRatio}} = ${{total}} / 1M tokens",
+  "（文字 + 音频）* 分组倍率 {{ratio}} = ${{total}}": "(Text + Audio) * Group ratio {{ratio}} = ${{total}}",
+  "文字提示 {{input}} tokens / 1M tokens * ${{price}} + 文字补全 {{completion}} tokens / 1M tokens * ${{compPrice}} +": "Text prompt {{input}} tokens / 1M tokens * ${{price}} + Text completion {{completion}} tokens / 1M tokens * ${{compPrice}} +",
   "提示 {{input}} tokens / 1M tokens * ${{price}} + 补全 {{completion}} tokens / 1M tokens * ${{compPrice}} * 分组 {{ratio}} = ${{total}}": "Prompt {{input}} tokens / 1M tokens * ${{price}} + Completion {{completion}} tokens / 1M tokens * ${{compPrice}} * Group {{ratio}} = ${{total}}",
   "价格：${{price}} * 分组：{{ratio}}": "Price: ${{price}} * Group: {{ratio}}",
   "模型: {{ratio}} * 分组: {{groupRatio}}": "Model: {{ratio}} * Group: {{groupRatio}}",

web/src/pages/Chat/index.js

@@ -34,8 +34,9 @@ const ChatPage = () => {
   return !isLoading && iframeSrc ? (
     <iframe
       src={iframeSrc}
-      style={{ width: '100%', height: '85vh', border: 'none' }}
+      style={{ width: '100%', height: '100%', border: 'none' }}
       title="Token Frame"
+      allow="camera;microphone"
     />
   ) : (
     <div>

web/src/pages/Token/EditToken.js

@@ -401,7 +401,7 @@ const EditToken = (props) => {
           <TextArea
             label={t('IP白名单')}
             name='allow_ips'
-            placeholder={t('允许的IP，一行一个')}
+            placeholder={t('允许的IP，一行一个，不填写则不限制')}
             onChange={(value) => {
               handleInputChange('allow_ips', value);
             }}