v0.13.8
juanfont/headscalev0.13.8Oct 11, 2026by tashfeenahmed
Upgrading?
AI Summary
This release removes blocking validation probes for LLMTR keys and adds support for Free.ai Kokoro text-to-speech.
Key Highlights
- LLMTR keys no longer trigger validation probes that could suspend accounts.
- Adds support for Free.ai Kokoro text-to-speech via /v1/audio/speech.
- Keys turn healthy automatically upon first successful request.
New Features
- LLMTR key handling improvements
- Kokoro text-to-speech support
Full Release Notes
FreeLLMAPI v0.13.8 stops the key checks LLMTR refuses and adds Free.ai Kokoro speech. ## Keys - **LLMTR keys no longer show a validation error.** LLMTR refuses automated key checks, so FreeLLMAPI no longer sends them. That removes the standing "rejected the key-validation probe" message and the repeated probes that LLMTR can suspend an account for. An LLMTR key shows as unchecked until it serves its first request, then turns healthy. Any key that has not been checked yet now also turns healthy on its first successful request. Thanks @kkvark for the report and @suantea for tracing it. (#1459, #1471) ## Providers - **Free.ai** speech: the Kokoro text-to-speech model through `/v1/audio/speech`, with standard OpenAI voice names mapped to Kokoro voices. (#1467) ## Updating Desktop users on v0.13.5 or later can update from inside the app: ⋯ → **Check for updates**. Docker: `ghcr.io/tashfeenahmed/freellmapi:v0.13.8`. The `latest` tag also points to this release. Existing keys and profiles are retained. This release has no database migrations. [Full changelog](https://github.com/tashfeenahmed/freellmapi/compare/v0.13.7...v0.13.8) --- ⭐ Like the free router? [Go Premium](https://freellmapi.co/?utm_source=github&utm_medium=release&utm_campaign=premium&utm_content=v0.13.8#pricing), the live signed catalog, $19/yr, cancel anytime.
Related Repositories
ollama/ollama★ 184,206
Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
fatedier/frp★ 110,051
A fast reverse proxy to help you expose a local server behind a NAT or firewall to the internet.
infiniflow/ragflow★ 92,612
RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs
gohugoio/hugo★ 90,198
The world’s fastest framework for building websites.
junegunn/fzf★ 83,716
:cherry_blossom: A command-line fuzzy finder