feat: support fish audio TTS

[leng-yue]

Checklist:

Important

Please review the checklist below before submitting your pull request.

• Please open an issue before creating a PR or link to an existing issue
• I have performed a self-review of my own code
• I have commented my code, particularly in hard-to-understand areas
• I ran dev/reformat(backend) and cd web && npx lint-staged(frontend) to appease the lint gods

Description

This PR add Fish Audio TTS support to dify Close #7984.

Type of Change

• Bug fix (non-breaking change which fixes an issue)
• New feature (non-breaking change which adds functionality)
• Breaking change (fix or feature that would cause existing functionality to not work as expected)
• This change requires a documentation update, included: Dify Document
• Improvement, including but not limited to code refactoring, performance optimization, and UI/UX improvement
• Dependency upgrade

Testing Instructions

Please describe the tests that you ran to verify your changes. Provide instructions so we can reproduce. Please also list any relevant details for your test configuration

• Test TTS with public English Voice, Normal Latency
• Test TTS with private English Voice, Low Latency

[leslie2046]

Cannot list my private models?
BTW ,i find that the API will return the private voice list if self=false, and not passing the language param.
@leng-yue

[leng-yue]

Cannot list my private models? BTW ,i find that the API will return the private voice list if self=false, and not passing the language param. @leng-yue

Let me take a look

[leng-yue]

Cannot list my private models? BTW ,i find that the API will return the private voice list if self=false, and not passing the language param. @leng-yue

I fixed the filtering behavior for language—it now filters based on the model language only, without the title language. I double-checked with self=false and without the language parameter on the API Playground and couldn't reproduce the issue.

[leslie2046]

@leng-yue OK,thank you

[leslie2046]

@leng-yue what's the difference between GPT-SoVITS and fish?which is better?

[cubxxw]

I hope that the client can configure TTS when calling the API of DIFY ChatFlow. Is it currently supported? Will you consider supporting it?

    "voice_preferences": {                  // 语音回复的偏好设置 (可选)
        "gender": "female",                 // 声音性别 (female, male)
        "voice_speed": "normal",            // 语速 (slow, normal, fast)
        "emotion": ["neutral"]              // 情绪选择 (neutral, happy, sad, etc.)
    },

[momomobinx]

这个好像不兼容本地部署的fish-speech 的api
https://speech.fish.audio/inference/#3-generate-vocals-from-semantic-tokens

python -m tools.api_server
--listen 0.0.0.0:8080
--llama-checkpoint-path "checkpoints/fish-speech-1.5"
--decoder-checkpoint-path "checkpoints/fish-speech-1.5/firefly-gan-vq-fsq-8x1024-21hz-generator.pth"
--decoder-config-name firefly_gan_vq