Unity制作批量配音制作工具

最新推荐文章于 2025-09-18 15:21:16 发布

原创

最新推荐文章于 2025-09-18 15:21:16 发布 · 1.3k 阅读

5 ·

CC 4.0 BY-SA版权

文章标签：

#语音识别

本文介绍了一个使用Unity制作的批量配音工具，通过调用讯飞语音合成API，实现了文本到语音的转换，并提供了详细的代码实现和配置流程。

最近一直在忙项目，都没有时间和大家分享文章了。今天是来送福利的，送个大家一个语音合成音频工具，当然这也是用Unity制作的。看到讯飞官网有个配音制作，还需要收费，我就不能忍啊，就把之前之前做的批量配音制作工具分享给大家。
在这里插入图片描述
就一段音频收这么贵，啧啧啧！！！

MSCDLL.cs 接口

using System;
using System.Runtime.InteropServices;

namespace msc
{
   
   
	public class MSCDLL
	{
   
   
		#region 登录登出
		[DllImport("msc_x64", CallingConvention = CallingConvention.StdCall)]
		public static extern int MSPLogin(string usr, string pwd, string parameters);



		[DllImport("msc_x64", CallingConvention = CallingConvention.StdCall)]
		public static extern int MSPLogout();
		#endregion

		#region 语音识别
		[DllImport("msc_x64", CallingConvention = CallingConvention.StdCall)]
		public static extern IntPtr QISRSessionBegin(string grammarList, string _params, ref int errorCode);



		[DllImport("msc_x64", CallingConvention = CallingConvention.StdCall)]
		public static extern int QISRAudioWrite(IntPtr sessionID, byte[] waveData, uint waveLen, AudioStatus audioStatus, ref EpStatus epStatus, ref RecogStatus recogStatus);



		[DllImport("msc_x64", CallingConvention = CallingConvention.StdCall)]
		public static extern IntPtr QISRGetResult(IntPtr sessionID, ref RecogStatus rsltStatus, int waitTime, ref int errorCode);



		[DllImport("msc_x64", CallingConvention = CallingConvention.StdCall)]
		public static extern int QISRSessionEnd(IntPtr sessionID, string hints);



		[DllImport("msc_x64", CallingConvention = CallingConvention.StdCall)]
		public static extern int QISRBuildGrammar(IntPtr grammarType, string grammarContent, uint grammarLength, string _params, GrammarCallBack callback, IntPtr userData);



		[System.Runtime.InteropServices.UnmanagedFunctionPointerAttribute(System.Runtime.InteropServices.CallingConvention.Cdecl)]
		public delegate int GrammarCallBack(int errorCode, string info, object udata);



		[DllImport("msc.dll", CallingConvention = CallingConvention.StdCall)]
		public static extern IntPtr QISRUploadData(string sessionID, string dataName, byte[] userData, uint lenght, string paramValue, ref int errorCode);
		#endregion

		#region 语音唤醒
		//定义回调函数
		[UnmanagedFunctionPointer(CallingConvention.Cdecl)]
		public delegate int ivw_ntf_handler(string sessionID, int msg, int param1, int param2, IntPtr info, IntPtr userData);



		//调用 QIVWSessionBegin(...)开始一次语音唤醒
		[DllImport("msc_x64", CallingConvention = CallingConvention.StdCall)]
		public static extern IntPtr QIVWSessionBegin(string grammarList, string _params, ref int errorCode);



		//调用 QIVWAudioWrite(...) 分块写入音频数据
		[DllImport("msc_x64", CallingConvention = CallingConvention.StdCall)]
		public static extern int QIVWAudioWrite(string sessionID, byte[] waveData, uint waveLen, AudioStatus audioStatus);



		[DllImport("msc_x64", CallingConvention = CallingConvention.StdCall)]
		public static extern int QIVWGetResInfo(string resPath, string resInfo, uint infoLen, string _params);



		//调用 QIVWRegisterNotify(...) 注册回调函数到msc。
		//如果唤醒成功，msc 调用回调函数通知唤醒成功息同时给出相应唤醒数据。如果出错，msc 调用回调函数给出错误信息
		[DllImport("msc_x64", CallingConvention = CallingConvention.StdCall)]
		public static extern int QIVWRegisterNotify(string sessionID, [MarshalAs(UnmanagedType.FunctionPtr)]ivw_ntf_handler msgProcCb, IntPtr userData);



		//调用 QIVWSessionEnd(...) 主动结束本次唤醒
		[DllImport("msc_x64", CallingConvention = CallingConvention.StdCall)]
		public static extern int QIVWSessionEnd(string sessionID, string hints);
		#endregion

		#region 语音合成

		[DllImport("msc_x64", CallingConvention = CallingConvention.StdCall)]
		public static extern IntPtr QTTSSessionBegin(string _params, ref int errorCode);



		[DllImport("msc_x64", CallingConvention = CallingConvention.StdCall)]
		public static extern int QTTSTextPut(IntPtr sessionID, string textString, uint textLen, string _params);



		[DllImport("msc_x64", CallingConvention = CallingConvention.StdCall)]
		public static extern IntPtr QTTSAudioGet(IntPtr sessionID, ref uint audioLen, ref SynthStatus synthStatus, ref int errorCode);



		[DllImport("msc_x64", CallingConvention = CallingConvention.StdCall)]
		public static extern IntPtr QTTSAudioInfo(IntPtr sessionID);



		[DllImport("msc_x64", CallingConvention = CallingConvention.StdCall)]
		public static extern int QTTSSessionEnd(IntPtr sessionID, string hints);
		#endregion
	}

	public enum Errors
	{
   
   
		MSP_SUCCESS = 0,
		MSP_ERROR_FAIL = -1,
		MSP_ERROR_EXCEPTION = -2,

		/* General errors 10100(0x2774) */
		MSP_ERROR_GENERAL = 10100,  /* 0x2774 */
		MSP_ERROR_OUT_OF_MEMORY = 10101,    /* 0x2775 */
		MSP_ERROR_FILE_NOT_FOUND = 10102,   /* 0x2776 */
		MSP_ERROR_NOT_SUPPORT = 10103,  /* 0x2777 */
		MSP_ERROR_NOT_IMPLEMENT = 10104,    /* 0x2778 */
		MSP_ERROR_ACCESS = 10105,   /* 0x2779 */
		MSP_ERROR_INVALID_PARA = 10106,     /* 0x277A */  /* 缺少参数 */
		MSP_ERROR_INVALID_PARA_VALUE = 10107,   /* 0x277B */  /* 无效参数值 */
		MSP_ERROR_INVALID_HANDLE = 10108,   /* 0x277C */
		MSP_ERROR_INVALID_DATA = 10109,     /* 0x277D */
		MSP_ERROR_NO_LICENSE = 10110,   /* 0x277E */  /* 引擎授权不足 */
		MSP_ERROR_NOT_INIT = 10111,     /* 0x277F */  /* 引擎未初始化,可能是引擎崩溃 */
		MSP_ERROR_NULL_HANDLE = 10112,  /* 0x2780 */
		MSP_ERROR_OVERFLOW = 10113,     /* 0x2781 */  /* 单用户下模型数超上限(10个), */
		/* 只出现在测试时对一个用户进行并发注册 */
		MSP_ERROR_TIME_OUT = 10114,     /* 0x2782 */  /* 超时 */
		MSP_ERROR_OPEN_FILE = 10115,    /* 0x2783 */
		MSP_ERROR_NOT_FOUND = 10116,    /* 0x2784 */  /* 数据库中模型不存在 */
		MSP_ERROR_NO_ENOUGH_BUFFER = 10117,     /* 0x2785 */
		MSP_ERROR_NO_DATA = 10118,  /* 0x2786 */  /* 从客户端读音频或从引擎段获取结果时无数据 */
		MSP_ERROR_NO_MORE_DATA = 10119,     /* 0x2787 */
		MSP_ERROR_NO_RESPONSE_DATA = 10120,     /* 0x2788 */
		MSP_ERROR_ALREADY_EXIST = 10121,    /* 0x2789 */  /* 数据库中模型已存在 */
		MSP_ERROR_LOAD_MODULE = 10122,  /* 0x278A */
		MSP_ERROR_BUSY = 10123,     /* 0x278B */
		MSP_ERROR_INVALID_CONFIG = 10124,   /* 0x278C */
		MSP_ERROR_VERSION_CHECK = 10125,    /* 0x278D */
		MSP_ERROR_CANCELED = 10126,     /* 0x278E */
		MSP_ERROR_INVALID_MEDIA_TYPE = 10127,   /* 0x278F */
		MSP_ERROR_CONFIG_INITIALIZE = 10128,    /* 0x2790 */
		MSP_ERROR_CREATE_HANDLE = 10129,    /* 0x2791 */
		MSP_ERROR_CODING_LIB_NOT_LOAD = 10130,  /* 0x2792 */
		MSP_ERROR_USER_CANCELLED = 10131,   /* 0x2793 */
		MSP_ERROR_INVALID_OPERATION = 10132,    /* 0x2794 */
		MSP_ERROR_MESSAGE_NOT_COMPLETE = 10133, /* 0x2795 */   /* flash */
		MSP_ERROR_NO_EID = 10134,   /* 0x2795 */
		MSP_ERROE_OVER_REQ = 10135,    /* 0x2797 */   /* client Redundancy request */
		MSP_ERROR_USER_ACTIVE_ABORT = 10136,    /* 0x2798 */   /* user abort */
		MSP_ERROR_BUSY_GRMBUILDING = 10137,    /* 0x2799 */
		MSP_ERROR_BUSY_LEXUPDATING = 10138,    /* 0x279A */
		MSP_ERROR_SESSION_RESET = 10139,    /* 0x279B */   /* msc主动终止会话，准备重传 */
		MSP_ERROR_BOS_TIMEOUT = 10140,    /* 0x279C */   /* VAD前端点超时 */
		MSP_ERROR_STREAM_FILTER = 10141,    /* 0X279D */   /* AIUI当前Stream被过滤 */
		MSP_ERROR_STREAM_CLEAR = 10142,    /* 0X279E */   /* AIUI当前Stream被清理 */

		/* Error codes of network 10200(0x27D8)*/
		MSP_ERROR_NET_GENERAL = 10200,  /* 0x27D8 */
		MSP_ERROR_NET_OPENSOCK = 10201,     /* 0x27D9 */   /* Open socket */
		MSP_ERROR_NET_CONNECTSOCK = 10202,  /* 0x27DA */   /* Connect socket */
		MSP_ERROR_NET_ACCEPTSOCK = 10203,   /* 0x27DB */   /* Accept socket */
		MSP_ERROR_NET_SENDSOCK = 10204,     /* 0x27DC */   /* Send socket data */
		MSP_ERROR_NET_RECVSOCK = 10205,     /* 0x27DD */   /* Recv socket data */
		MSP_ERROR_NET_INVALIDSOCK = 10206,  /* 0x27DE */   /* Invalid socket handle */
		MSP_ERROR_NET_BADADDRESS = 10207,   /* 0x27EF */   /* Bad network address */
		MSP_ERROR_NET_BINDSEQUENCE = 10208,     /* 0x27E0 */   /* Bind after listen/connect */
		MSP_ERROR_NET_NOTOPENSOCK =