TTS-API
TTS-API is a REST API service that converts text into spoken Catalan for local projects, letting other programs generate voiceovers, read documents aloud, or…
Platform availability
Available on 0 of 10 platforms
- Unraid (not listed)
- TrueNAS (not listed)
- Umbrel (not listed)
- ZimaOS (not listed)
- Proxmox (not listed)
- Helm (not listed)
- Mac (not listed)
- Windows (not listed)
- Linux (not listed)
- 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.
15/100 Low
- Maintained
- 0last commit 977 days ago
- Popular
- 3136 GitHub stars
- Easy to install
- 250 install platforms, install notes, Docker image
- Light to run
- 1016 GB minimum RAM
- Security check
- 201 serious finding, 6 minor, CI, OpenSSF Scorecard 2.8/10
Security check: 1 serious finding
- Uses proxy-addr 2.0.7, which has a known critical vulnerability (npm)
Automated checks on commit b968589, 15 Nov 2026. Not an audit.
- GitHub stars
- 36
- Open issues
- 6
- Last commit
- 2024-03-19
- Latest release
- v2.6.1
- License
- MIT
- Activity
- stale
Checked 3 days ago - source: GitHub (pedroetb/tts-api)
Resources & Compatibility
Minimum requirements: 16 GB RAM. ARM (e.g. Raspberry Pi) is not supported.
Checked 54 days ago - source: Docker Hub image tags and published docs
First-install notes
- Start the TTS server and open port 5002 Run the TTS server container (a packaged app started with Docker) and keep port 5002 reachable. Port 5002 is the address other programs use to ask the server for audio, so if it is not reachable the app looks offline and cannot produce speech. source
- Choose a voice model before using the API After the server is running, use the model list command to see available voices and start the one you want. Without a selected model, the app has no voice to turn your text into audio. source
- Use GPU only if you have one If you have an NVIDIA GPU (graphics card), use the GPU image with --gpus all and --use_cuda; otherwise use the CPU image (the version that runs on the main processor). This keeps startup from failing when no compatible GPU is present and makes speech faster when one is available. source
- Setup Install one supported TTS engine (GoogleSpeech, gTTS, Festival, or eSpeak), Node.js, and npm, then run npm install and npm start. source
Fetched 42 days ago - each note links to its source
Variants
Alternatives
No alternatives collected yet.
Common questions
How do I install the required TTS engines before running the project manually?
Install one or more supported engines such as GoogleSpeech, gTTS, Festival, or eSpeak using the provided package and pip commands. You also need Node.js and npm, then run npm install and npm start.
How can the Docker Swarm deployment be reverse proxied?
The service is prepared for Traefik and is intended to be reachable at the tts subdomain of the domain you configure. Caddy is used because Docker Swarm does not support device configuration and Traefik cannot proxy Docker containers and Swarm services together, so Caddy fronts the tts-api container.
How do clients request audio from the running API?
Send POST requests to the API endpoint, or use the built-in web form at the root URL. Both local audio playback and downloading the audio file are available using different voice codes.
Answers sourced from github.com
Community
- Huge problems with TTS API - OpenAI API Community Forum (other)
- TTS API service usability - API - OpenAI Developer Community (other)
- Build More Immersive Experiences: Text-to-Speech API Full Release (forum)
- Text-to-Speech API Update - New Voices and New Languages (forum)
Collected 48 days ago - public community threads