From 1d4ff796d79a49cd173e27121a365d7925305932 Mon Sep 17 00:00:00 2001
From: SSMario <sumeirui@outlook.com>
Date: Tue, 16 May 2023 11:50:54 +0800
Subject: [PATCH] =?UTF-8?q?feat:=20=E5=A2=9E=E5=8A=A0eleventLabs?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 config.py                      |  2 +-
 requirements-optional.txt      |  1 +
 voice/elevent/elevent_voice.py | 32 ++++++++++++++++++++++++++++++++
 voice/factory.py               |  4 ++++
 4 files changed, 38 insertions(+), 1 deletion(-)
 create mode 100644 voice/elevent/elevent_voice.py

diff --git a/config.py b/config.py
index ae1cfd7..782beac 100644
--- a/config.py
+++ b/config.py
@@ -53,7 +53,7 @@ available_setting = {
     "voice_reply_voice": False,  # 是否使用语音回复语音，需要设置对应语音合成引擎的api key
     "always_reply_voice": False,  # 是否一直使用语音回复
     "voice_to_text": "openai",  # 语音识别引擎，支持openai,baidu,google,azure
-    "text_to_voice": "baidu",  # 语音合成引擎，支持baidu,google,pytts(offline),azure
+    "text_to_voice": "baidu",  # 语音合成引擎，支持baidu,google,pytts(offline),azure,eleven
     # baidu 语音api配置， 使用百度语音识别和语音合成时需要
     "baidu_app_id": "",
     "baidu_api_key": "",
diff --git a/requirements-optional.txt b/requirements-optional.txt
index c248689..9901de4 100644
--- a/requirements-optional.txt
+++ b/requirements-optional.txt
@@ -9,6 +9,7 @@ baidu_aip>=4.16.10 # baidu voice
 azure-cognitiveservices-speech # azure voice
 numpy<=1.24.2
 langid # language detect
+elevenlabs==0.2.15
 
 #install plugin
 dulwich
diff --git a/voice/elevent/elevent_voice.py b/voice/elevent/elevent_voice.py
new file mode 100644
index 0000000..72d5bcd
--- /dev/null
+++ b/voice/elevent/elevent_voice.py
@@ -0,0 +1,32 @@
+"""
+eleventLabs voice service
+"""
+
+import time
+
+from elevenlabs import generate
+
+from bridge.reply import Reply, ReplyType
+from common.log import logger
+from common.tmp_dir import TmpDir
+from voice.voice import Voice
+
+
+class ElevenLabsVoice(Voice):
+
+    def __init__(self):
+        pass
+
+    def voiceToText(self, voice_file):
+        pass
+
+    def textToVoice(self, text):
+        audio = generate(
+            text=text
+        )
+        fileName = TmpDir().path() + "reply-" + str(int(time.time())) + "-" + str(hash(text) & 0x7FFFFFFF) + ".mp3"
+        with open(fileName, "wb") as f:
+            f.write(audio)
+        logger.info("[ElevenLabs] textToVoice text={} voice file name={}".format(text, fileName))
+        return Reply(ReplyType.VOICE, fileName)
+
diff --git a/voice/factory.py b/voice/factory.py
index 45fe0d1..0cf1a05 100644
--- a/voice/factory.py
+++ b/voice/factory.py
@@ -29,4 +29,8 @@ def create_voice(voice_type):
         from voice.azure.azure_voice import AzureVoice
 
         return AzureVoice()
+    elif voice_type == "eleven":
+        from voice.elevent.elevent_voice import ElevenLabsVoice
+
+        return ElevenLabsVoice()
     raise RuntimeError