Jules 421561627017222020 9715bed7#12
Open
MahammadWahab540 wants to merge 40 commits into
Open
Conversation
…or-performance-logging Add concise OpenAI speech performance logging and request ID
…r-openmaic-app docs: add OpenMAIC / Pathwisse TTS static audit
…request-validation Validate OpenAI speech request inputs
…ng-in-server.py Preserve HTTP exceptions in speech endpoint
…pu-for-cpu-setup Add CPU Dockerfile and Railway build config
…check-environment-variable Prefer PORT environment variable for server port
…-conditionally-open-browser Gate browser auto-open behind explicit local dev flag
…script-and-docker-support Bake default KittenTTS model into CPU image
…-options-in-load_model Configure ONNX Runtime session options
…r-espeak-ng-library-paths Configure POSIX eSpeak library discovery and install libespeak-ng1 in Docker images
…tion-for-cpu-detection Use ONNX Runtime for device detection and remove CPU-only PyTorch dependency
…n-in-engine.py Add TTS warmup, warmup health state, and /health endpoint
…ndpoint-in-server.py Add /health endpoint and ONNX provider reporting
…ch_endpoint-for-text-synthesis OpenAI /v1/audio/speech: stream WAV sentence chunks and add timing logs
…endpoint-with-streaming-mode Add chunked streaming mode to /tts endpoint
Co-authored-by: MahammadWahab540 <[email protected]>
…P3, sanitize CORS/config - Fail closed when TTS_API_KEY unset (protected endpoints return 503, never public) - verify_api_key supports Bearer and X-API-Key (hmac.compare_digest) - ENABLE_MANAGEMENT_ENDPOINTS / ENABLE_WEB_UI default to false (safe) - /api/ui/initial-data gated behind Web UI + key and config sanitized - Fix /v1/audio/speech WAV streaming: keep first chunk RIFF header (chunk_index > 1) - MP3 rejected with clear HTTP 400 on /tts and /v1/audio/speech (Option B) - CORS uses ALLOWED_ORIGINS allow-list, allow_credentials=False (no wildcard) - config.yaml cleaned: removed debug last_text blob, Linux log path, use_auth placeholder - README documents required env, auth, formats, Railway, safe defaults - Add/expand pytest coverage for all fixes (24 passing)
…id WAV - /tts, /api/tts/speak (stream=true) and /v1/audio/speech now collect all chunk audio arrays, concatenate, and encode ONCE so the final WAV has a single correct RIFF/data header describing the full length (no truncation) - Removed per-chunk header stripping / standalone-WAV streaming behavior - Updated X-TTS-WAV-Streaming-Note to honestly state single valid WAV output - Added latency headers (X-TTS-Total-Time-Ms, X-TTS-Inference-Time-Ms, X-TTS-Model, X-TTS-Voice) to all TTS responses - Removed dead commented torch/torchaudio lines from utils.py - Strengthened streaming tests: exactly one RIFF, getnframes reflects total, readframes returns full PCM, duration > single chunk, latency headers present - 25 tests passing
…anup config/utils Co-authored-by: MahammadWahab540 <[email protected]>
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.
No description provided.