How can the API provided by ChatGPT-Sovits v2 be integrated into Dify to achieve text-to-speech functionality for response outputs?

[sums2001]

Self Checks

• I have searched for existing issues search for existing issues, including closed ones.
• I confirm that I am using English to submit this report (我已阅读并同意 Language Policy).
• [FOR CHINESE USERS] 请务必使用英文提交 Issue，否则会被关闭。谢谢！:）
• Please do not modify this template :) and fill in all the required fields.

Content

I have successfully deployed the Dify and Sovits APIs. Among them, the Sovits API can generate voice output normally.

The API format for submitting to Sovits API v2 is as follows:
http://192.168.3.119:9880/tts?text=你好！很高兴为你提供帮助。你可以问我任何问题了。&text_lang=zh&ref_audio_path=H:\AI\GPT-SoVITS_V2_250113\ref\fx.wav&prompt_text=当负面情绪涌上心头时，我们总是禁不住想要判断对方&prompt_lang=zh&text_split_method=cut5&batch_size=3&batch_threshold=0.75&speed_factor=1

I believe this can be accomplished through the development of custom tools and workflows, which I have begun to explore.This is the code for the custom tool.
{ "openapi": "3.1.0", "info": { "title": "GPT-SoVITS_TTS", "description": "动态参数增强版语音合成接口", "version": "v2.3.2" }, "servers": [ { "url": "http://192.168.3.119:9880" } ], "paths": { "/tts": { "get": { "description": "多参数控制语音合成", "operationId": "GenerateTTS", "parameters": [ { "name": "text", "in": "query", "required": true, "schema": { "type": "string" } }, { "name": "prompt_text", "in": "query", "required": true, "schema": { "type": "string" } }, { "name": "text_lang", "in": "query", "schema": { "type": "string", "default": "zh" } }, { "name": "prompt_lang", "in": "query", "schema": { "type": "string", "default": "zh" } }, { "name": "ref_audio_path", "in": "query", "schema": { "type": "string", "default": "H:\\AI\\GPT-SoVITS_V2_250113\\ref\\fx.wav" } }, { "name": "text_split_method", "in": "query", "schema": { "type": "string", "enum": ["cut0", "cut1", "cut5"], "default": "cut5" } }, { "name": "batch_size", "in": "query", "schema": { "type": "integer", "minimum": 1, "maximum": 10, "default": 3 } }, { "name": "speed_factor", "in": "query", "schema": { "type": "number", "minimum": 0.5, "maximum": 2.0, "default": 1.0 } } ], "responses": { "200": { "description": "成功生成语音文件", "content": { "application/json": { "schema": { "type": "object", "properties": { "url": { "type": "string", "description": "生成的语音文件URL" }, "files": { "type": "array", "items": { "type": "string" }, "description": "生成的语音文件URL列表" } } } } } } } } } } }

The following is the DSL file of the workflow.

app: description: AI对话语音助手 - 将AI对话内容转换为语音输出 icon: 🎙️ icon_background: '#FFEAD5' mode: advanced-chat name: AI对话语音助手 use_icon_as_answer_icon: false kind: app version: 0.1.5 workflow: conversation_variables: [] environment_variables: [] features: file_upload: allowed_file_extensions: - .JPG - .JPEG - .PNG - .GIF - .WEBP - .SVG - .WAV - .MP3 allowed_file_types: - image - audio allowed_file_upload_methods: - local_file - remote_url enabled: true fileUploadConfig: audio_file_size_limit: 50 batch_count_limit: 5 file_size_limit: 15 image_file_size_limit: 10 video_file_size_limit: 100 workflow_file_upload_limit: 10 image: enabled: false number_limits: 3 transfer_methods: - local_file - remote_url number_limits: 3 opening_statement: 欢迎使用AI对话语音助手！请输入您的问题，我会将回答转换为语音。 retriever_resource: enabled: false sensitive_word_avoidance: enabled: false speech_to_text: enabled: false suggested_questions: [] suggested_questions_after_answer: enabled: false text_to_speech: enabled: false language: '' voice: '' graph: edges: - data: isInIteration: false sourceType: start targetType: llm id: start-llm source: start sourceHandle: source target: llm targetHandle: target type: custom zIndex: 0 - data: isInIteration: false sourceType: llm targetType: tool id: llm-tool source: llm sourceHandle: source target: tts_tool targetHandle: target type: custom zIndex: 0 - data: isInIteration: false sourceType: tool targetType: answer id: tool-answer source: tts_tool sourceHandle: source target: answer targetHandle: target type: custom zIndex: 0 - data: isInIteration: false sourceType: tool targetType: answer id: tool-answer2 source: tts_tool sourceHandle: source target: answer2 targetHandle: target type: custom zIndex: 0 nodes: - data: desc: 开始对话 selected: false title: 开始 type: start variables: [] height: 80 id: start position: x: 80 y: 282 positionAbsolute: x: 80 y: 282 selected: false sourcePosition: right targetPosition: left type: custom width: 243 - data: context: enabled: true variable_selector: [] desc: AI对话模型 memory: role_prefix: assistant: '' user: '' window: enabled: true size: 10 model: completion_params: temperature: 0.7 mode: chat name: qwen2.5:latest provider: ollama prompt_template: - id: system-prompt role: system text: 你是一个友好的AI助手，请用简洁明了的语言回答用户的问题。 - id: user-prompt role: user text: '{{#sys.query#}}' selected: false title: LLM type: llm variables: [] vision: enabled: false height: 124 id: llm position: x: 380 y: 282 positionAbsolute: x: 380 y: 282 selected: false sourcePosition: right targetPosition: left type: custom width: 243 - data: desc: 文本转语音 provider_id: 6d69622c-642c-4513-9127-802b9c0ef327 provider_name: GPT-SoVITS_TTS_new2 provider_type: api selected: false title: GenerateTTS tool_configurations: {} tool_label: GenerateTTS tool_name: GenerateTTS tool_parameters: batch_size: type: constant value: 3 prompt_lang: type: mixed value: zh prompt_text: type: mixed value: 当负面情绪涌上心头时，我们总是禁不住想要判断对方 ref_audio_path: type: mixed value: H:\AI\GPT-SoVITS_V2_250113\ref\fx.wav speed_factor: type: constant value: 1 text: type: mixed value: '{{#llm.text#}}' text_lang: type: mixed value: zh text_split_method: type: mixed value: cut5 type: tool height: 80 id: tts_tool position: x: 646.3606747855553 y: 289.1717846545598 positionAbsolute: x: 646.3606747855553 y: 289.1717846545598 selected: true sourcePosition: right targetPosition: left type: custom width: 243 - data: answer: '{{#llm.text#}}\n\n[点击播放语音]({{#tts_tool.files#}})' desc: 显示回复和语音状态 selected: false title: 回复 type: answer variables: [] height: 148 id: answer position: x: 1011.1895211266806 y: 334.31790640604515 positionAbsolute: x: 1011.1895211266806 y: 334.31790640604515 selected: false sourcePosition: right targetPosition: left type: custom width: 243 - data: answer: 语音文件已生成：{{#tts_tool.files#}} desc: '' selected: false title: 语音文件 type: answer variables: [] height: 117 id: answer2 position: x: 1011.1895211266806 y: 504.31790640604515 positionAbsolute: x: 1011.1895211266806 y: 504.31790640604515 selected: false sourcePosition: right targetPosition: left type: custom width: 243 viewport: x: -283.69555528485046 y: -120.59900952601663 zoom: 0.8652607146560651

After completing the above operation, normal conversation is possible, but there is no voice output.Could someone help me figure out where the problem lies? Thank you!