github-starred/templates
2
0
Fork 1
mirror of https://github.com/Dokploy/templates.git synced 2026-03-08 22:52:20 -05:00
Code Issues 155 Packages Projects Releases Wiki Activity

[PR #403] feat: Add Kokoro TTS FastAPI template (#353) #432

New Issue
Open
opened 2025-11-22 20:38:31 -06:00 by GiteaMirror · 0 comments
GiteaMirror commented 2025-11-22 20:38:31 -06:00
Owner
Copy Link

📋 Pull Request Information

Original PR: https://github.com/Dokploy/templates/pull/403
Author: @Harikrishnan1367709
Created: 9/29/2025
Status: 🔄 Open

Base: main ← Head: Kokoro-TTS-#353

📝 Commits (3)

  • b050301 feat: Add Kokoro TTS FastAPI template (#353) - Add CPU-optimized docker-compose.yml with source build - Add GPU-optimized docker-compose-gpu.yml for NVIDIA support - Add comprehensive template.toml with OpenAI-compatible API docs - Add kokoro-tts.svg logo and meta.json entry - Support streaming audio, timestamps, and multi-language TTS - Resolves #353
  • bf1bc3c updated the meta.json for the build errors
  • 737592a removed the docker-compose-gpu.yml file

📊 Changes

4 files changed (+127 additions, -0 deletions)

View changed files

➕ blueprints/kokoro-tts/docker-compose.yml (+24 -0)
➕ blueprints/kokoro-tts/kokoro-tts.svg (+12 -0)
➕ blueprints/kokoro-tts/template.toml (+72 -0)
📝 meta.json (+19 -0)

📄 Description

Description

Implements Kokoro TTS FastAPI template for #353. Provides Dockerized FastAPI wrapper for Kokoro-82M text-to-speech model with OpenAI-compatible endpoints.

Features

  • Multi-language TTS (English, Japanese, Chinese)
  • OpenAI-compatible API (/v1/audio/speech)
  • CPU & GPU support (separate compose files)
  • Streaming audio with word-level timestamps
  • Web interface and interactive docs

Files Added

  • blueprints/kokoro-tts/docker-compose.yml - CPU version
  • blueprints/kokoro-tts/docker-compose-gpu.yml - GPU version
  • blueprints/kokoro-tts/template.toml - Dokploy config
  • blueprints/kokoro-tts/kokoro-tts.svg - Logo
  • Updated meta.json with template entry

API Endpoints

  • POST /v1/audio/speech - OpenAI-compatible speech generation
  • POST /dev/captioned_speech - Speech with timestamps
  • POST /dev/phonemize - Text to phonemes
  • GET /docs - Interactive API docs
  • GET /web - Web interface
Screenshot 2025-09-29 at 6 10 16 PM

Closes #353

🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.

## 📋 Pull Request Information **Original PR:** https://github.com/Dokploy/templates/pull/403 **Author:** [@Harikrishnan1367709](https://github.com/Harikrishnan1367709) **Created:** 9/29/2025 **Status:** 🔄 Open **Base:** `main` ← **Head:** `Kokoro-TTS-#353` --- ### 📝 Commits (3) - [`b050301`](https://github.com/Dokploy/templates/commit/b0503016415b376e9fe2a9a07e1481a9a4b68e5d) feat: Add Kokoro TTS FastAPI template (#353) - Add CPU-optimized docker-compose.yml with source build - Add GPU-optimized docker-compose-gpu.yml for NVIDIA support - Add comprehensive template.toml with OpenAI-compatible API docs - Add kokoro-tts.svg logo and meta.json entry - Support streaming audio, timestamps, and multi-language TTS - Resolves #353 - [`bf1bc3c`](https://github.com/Dokploy/templates/commit/bf1bc3ce0444bb96d2c33f5402c89135ab053c77) updated the meta.json for the build errors - [`737592a`](https://github.com/Dokploy/templates/commit/737592adf6955817f6bafdd2d8e7daa370833cc3) removed the docker-compose-gpu.yml file ### 📊 Changes **4 files changed** (+127 additions, -0 deletions) <details> <summary>View changed files</summary> ➕ `blueprints/kokoro-tts/docker-compose.yml` (+24 -0) ➕ `blueprints/kokoro-tts/kokoro-tts.svg` (+12 -0) ➕ `blueprints/kokoro-tts/template.toml` (+72 -0) 📝 `meta.json` (+19 -0) </details> ### 📄 Description ## Description Implements Kokoro TTS FastAPI template for #353. Provides Dockerized FastAPI wrapper for Kokoro-82M text-to-speech model with OpenAI-compatible endpoints. ## Features - **Multi-language TTS** (English, Japanese, Chinese) - **OpenAI-compatible API** (`/v1/audio/speech`) - **CPU & GPU support** (separate compose files) - **Streaming audio** with word-level timestamps - **Web interface** and interactive docs ## Files Added - `blueprints/kokoro-tts/docker-compose.yml` - CPU version - `blueprints/kokoro-tts/docker-compose-gpu.yml` - GPU version - `blueprints/kokoro-tts/template.toml` - Dokploy config - `blueprints/kokoro-tts/kokoro-tts.svg` - Logo - Updated `meta.json` with template entry ## API Endpoints - `POST /v1/audio/speech` - OpenAI-compatible speech generation - `POST /dev/captioned_speech` - Speech with timestamps - `POST /dev/phonemize` - Text to phonemes - `GET /docs` - Interactive API docs - `GET /web` - Web interface <img width="1009" height="814" alt="Screenshot 2025-09-29 at 6 10 16 PM" src="https://github.com/user-attachments/assets/309c9928-9b20-493e-81d8-79abd1ebf004" /> Closes #353 --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>
GiteaMirror added the pull-request label 2025-11-22 20:38:31 -06:00
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
bug
documentation
pull-request
Mirrored from GitHub Pull Request
 template
No Label pull-request
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/templates#432
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?