audio.cpp TTS: restart the server after an engine update - #14525
Merged
Conversation
The engine installer extracted the new audiocpp_server while a server started from the previous build was still running, and the Higgs/Fish/IndexTTS engines kept reusing that process for the rest of the session. With the 2026-09-04 build that surfaced as "unsupported model family hint: higgs_audio_tts" on Test voice, because the old August binary only had index_tts2 compiled in. - TtsVoiceInstaller.EnsureAudioCppRuntime stops all three audio.cpp servers before downloading (on Windows the running exe could not be overwritten). - Each engine records the server binary's size + mtime when it launches and restarts when that changes, so a replaced binary is never reused. Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Follow-up to #14522. After updating the audio.cpp runtime, Test voice with Higgs Audio v3 failed with:
The tools log showed why: the Higgs server was launched from the old August binary at 17:17:58, the new archive was extracted over it at 17:18:47 while that process was still running, and every later request reused the running process. The old build only had
index_tts2compiled in, so the registry rejected the family.TtsVoiceInstaller.EnsureAudioCppRuntimenow stops all three audio.cpp servers (IndexTTS 2.5, Higgs, Fish) before downloading. On Windows this also matters because a running exe cannot be overwritten.AudioCppRuntime.GetServerExecutableStamp()returns the binary's size + mtime; each engine records it at launch and restarts the server when it changes, so a replaced binary (update, manual copy) is never reused.Verification
dotnet test --filter AudioCpp: 11 passed.higgs-tts-server.json(model file path) answers 200 when launched fresh.🤖 Generated with Claude Code