Open-Source Audio Model Searches Apollo 11 Recordings
BanghuaZ · x · 2026-07-12
OpenMOSS has released MOSS-Transcribe-Diarize, an open-source 0.9B model under the Apache 2.0 license.
This model combines transcription, diarization, and timestamping into a single pass, with its core advantage being suitability for long audio inputs.
The provided real-world test case involves:
- Processing 174 hours of Apollo 11 mission audio into searchable content
- A total cost of just $9.46
- Using original NASA recordings preserved by the Internet Archive
- Processing a total of 103 audio segments
- Completion via a single Hugging Face Job in 3.8 hours, at a speed of roughly 47x realtime
- Generating 45,355 timestamped speaker segments
The author notes that users can now search these mission recordings by "who said what and when."
Related event: Open_MOSS Releases Apollo Audio Transcription Model(2 posts)→
More from Multimodal
- 3D ResNet Paper Crosses 3,000 Citations Eight Years After CVPR 2018 — HirokatuKataoka · 2026-09-11
- Non-coder builds full-featured Android ComfyUI client with ChatGPT, submits to Google Play — ComfierUI · 2026-09-11
- RunningHub open-sources H3Lightning, speeding up MiniMax H3 video generation 12x — 智东西 · 2026-09-11
- FastH3-Live hits 22fps: acceleration node benchmarks and the --vram-headroom trick — spartong945 · 2026-09-11
- Midjourney style code share: --sref 2912175708 — tisch_eins · 2026-09-11
- Astra storyboards plus Minimax H3 per-shot generation boost video success rates — Hailuo_AI · 2026-09-11