Spaces:

ArtFix0
/

reachy_conv_app

Running

App Files Files Community

reachy_conv_app

678 MB

Ctrl+K

1 contributor

History: 94 commits

ArtFix0

v0.5.43.6: hotfix dashboard save ReferenceError broke every TTS engine except edge

8fcf3e3 verified 10 days ago

assets
Local-stack Reachy Conv: drop OpenAI realtime path, ship Ollama/Parakeet/Silero/Qwen stack 17 days ago
src
v0.5.43.6: hotfix dashboard save ReferenceError broke every TTS engine except edge 10 days ago
tests
v0.5.43.1: fix silent LLM-reply audio — use shape-aware _synth_result_to_pcm in _synth_and_push_sentence 10 days ago
wheels
v0.5.21: fat wheel for Windows install deadlock fix + qwentts dormant 11 days ago
.gitattributes

492 Bytes
v0.5.43.2: natural human speech across all TTS engines 10 days ago
.gitignore

961 Bytes
v0.4.1: ship logs streaming fix, LLM knobs, bundled ffmpeg 16 days ago
LICENSE

11.4 kB
Local-stack Reachy Conv: drop OpenAI realtime path, ship Ollama/Parakeet/Silero/Qwen stack 17 days ago
README.md

149 kB
v0.5.43.6: hotfix dashboard save ReferenceError broke every TTS engine except edge 10 days ago
_publish_v040.py

1.86 kB
v0.4.0: edge-tts as built-in TTS engine with rate/volume/pitch knobs 17 days ago
config.example.yaml

13.1 kB
v0.5.43.5: batched playback (full reply as one continuous utterance) 10 days ago
index.html

31.2 kB
Cyberpunk redesign of the static Space front page 16 days ago
pyproject.toml

13.2 kB
v0.5.43.6: hotfix dashboard save ReferenceError broke every TTS engine except edge 10 days ago
setup.py

2.09 kB
v0.5.29: per-app venv on first launch (Windows chatterbox fix) 11 days ago
style.css

15.9 kB
Cyberpunk redesign of the static Space front page 16 days ago
upload_v0.5.3.py

6.88 kB
v0.5.3: streaming LLM + sentence-chunked TTS so audio starts the moment the first sentence is complete. 12 days ago
upload_v0.5.30.py

12.5 kB
v0.5.30: dashboard SHUTDOWN button + clean app-close path (Ollama left alone) 11 days ago
upload_v0.5.31.py

16.2 kB
v0.5.31: ship `gi` shim for Windows + bind pydub to imageio-ffmpeg at module-load 10 days ago
upload_v0.5.32.py

5.72 kB
v0.5.32: make `gi` shim probe a 2-line check (catches gstreamer-python partial-install) 10 days ago
upload_v0.5.32_hotfix.py

1.5 kB
v0.5.32 (hotfix): correct README test counts (no failures, 7 self-skip) 10 days ago
upload_v0.5.33.py

7.52 kB
v0.5.33: `gi` shim now overwrites partial `gi/` from gstreamer-python 10 days ago
upload_v0.5.34.py

6.59 kB
v0.5.34: pre-register `gi` shim in sys.modules at top of main.py 10 days ago
upload_v0.5.35.py

7.58 kB
v0.5.35: fix gstreamer isinstance crash in mic_pump (v0.5.34 regression) 10 days ago
upload_v0.5.36.py

8.47 kB
v0.5.36: TTS thinking filler on every backend + gi shim as fallback only + reachy-mini 1.9.0 10 days ago
upload_v0.5.37.py

7.9 kB
v0.5.37: thinking filler plays the full phrase + reverted prod audio path 10 days ago
upload_v0.5.38.py

7.34 kB
v0.5.38: bundle the `gi` shim INSIDE the wheel as a real sub-package 10 days ago
upload_v0.5.39.py

7.79 kB
v0.5.39: expand the gi shim's _GstModule to cover every Gst type the SDK references 10 days ago
upload_v0.5.40.py

1.26 kB
v0.5.40: force media_backend=webrtc when gi shim is active 10 days ago
upload_v0.5.41.py

4.08 kB
v0.5.41: cover every gstreamer call site the SDK's WebRTC backend init makes 10 days ago
upload_v0.5.42.py

5.53 kB
v0.5.42: real gstreamer, no fake shim — auto-install on first run 10 days ago
upload_v0.5.43.1.py

6.47 kB
v0.5.43.1: fix silent LLM-reply audio — use shape-aware _synth_result_to_pcm in _synth_and_push_sentence 10 days ago
upload_v0.5.43.py

4.71 kB
v0.5.43: wire nested gi into sys.path — real fix for v0.5.42 Windows install bug 10 days ago
uv.lock

1.15 MB
v0.5.43.2: natural human speech across all TTS engines 10 days ago