TTS Now

TTS Now is a cross-platform desktop text-to-speech (TTS) tool that converts your text into spoken audio by calling cloud speech-synthesis APIs from providers…

  • AI
  • Tools & Utilities
TTS Now is a cross-platform desktop text-to-speech (TTS) tool that converts your text into spoken audio by calling cloud speech-synthesis APIs from providers such as Alibaba Cloud and iFlytek. It supports quick one-off and batch synthesis on Windows, macOS, and Linux, giving desktop users a simple way to generate speech from their own cloud accounts.

Platform availability

Available on 3 of 10 platforms

  • Unraid (not listed)
  • TrueNAS (not listed)
  • Umbrel (not listed)
  • ZimaOS (not listed)
  • Proxmox (not listed)
  • Helm (not listed)
  • Mac
  • Windows
  • Linux
  • Any server (not listed)

Health score?A 0-100 score computed nightly from four factors: maintained (40%: recent commits and steady activity), popular (25%: GitHub stars, log scale), easy to install (20%: platforms, install notes, setup guides, Docker image) and light to run (15%: minimum RAM, ARM support). When the source code has been checked, a fifth factor, security check (20%: automated scan for committed secrets, unsafe desktop-app settings, known-vulnerable dependencies and project hygiene; any serious finding caps it at 20), is added. Factors without data are left out and the rest are rescaled.

24/100 Low

Maintained
0last commit 1411 days ago
Popular
51371 GitHub stars
Easy to install
553 install platforms, install notes, Docker image
Light to run
108 GB minimum RAM
Security check
201 serious finding, CI
GitHub stars
371
Open issues
3
Last commit
2023-01-10
Latest release
1.0.6
License
Apache-2.0
Activity
stale

Checked 2 days ago - source: GitHub (funnyzak/tts-now)

Resources & Compatibility

Minimum requirements: 8 GB RAM, 5 GB disk.

Checked 54 days ago - source: Docker Hub image tags and published docs

First-install notes

  • Open port 2525 for the Jupyter setup page The Docker setup starts a Jupyter Notebook (a web-based coding workspace) on port 2525, which you use to pick speakers. If you access it from another device, open or allow port 2525 on your network or firewall, or the browser connection will not reach it. source
  • Set your GPU number before training If you plan to train on an NVIDIA GPU, put your GPU device ID in CUDA_VISIBLE_DEVICES, for example 0. Without it, the job may use the CPU, be much slower, or fail to use the GPU at all. source
  • Keep config and model files in place Training and fine-tuning need exact paths to files like config.json and model_file.pth, often under your user profile’s .local/share/tts folder. If you move, rename, or delete them, the training command will not find the model settings and will stop. source
  • Get the app and configure your cloud provider Download the latest desktop build from the GitHub releases page, then enter your cloud text-to-speech provider credentials (such as Alibaba Cloud or iFlytek API keys) in the app settings before you can generate speech. source

Fetched 42 days ago - each note links to its source

Alternatives

No alternatives collected yet.

Common questions

Do I need to provide cloud provider credentials in TTS Now?

Yes, TTS Now uses cloud TTS APIs. For Aliyun you need a speech synthesis AppKey and an account API Key, and for Xfyun you register an account on Xfyun.

Why might a specific Xfyun voice not work?

Some Xfyun voices require you to add scenario support for them in the Xfyun console before they can be used.

Can TTS Now synthesize more than one text at a time?

Yes, it supports single-text quick synthesis and batch synthesis.

How can I reset TTS Now's configuration?

The configuration dialog includes a clear configuration button.

Answers sourced from github.com

Community

Collected 48 days ago - public community threads