Photon 2.1 expands streaming ASR for self-hosted deployments
Moondream says Photon 2.1 adds streaming speech recognition for three models and beats each model’s reference engine in all comparable tests.
Source: Photon 2.1 adiciona reconhecimento de fala em streaming (moondream.ai). Text prepared with AI from this source.
What happened and what to do
In a post published on September 2, 2026, Moondream said Photon 2.1 adds streaming automatic speech recognition for Whisper, Qwen3-ASR, and Parakeet, and support for the NVIDIA B200 GPU. The company says the system outperformed each model’s reference engine in all comparable tests.
To evaluate self-hosted ASR, a company can test representative audio samples, compare transcription quality and latency across models and GPUs, and monitor the service in production. An implementation could include secure audio collection, a transcription API, and a dashboard for tracking performance and failures.
How the consultancy can help
Wendelmaques can diagnose audio, privacy, and performance requirements, scope an evaluation, and implement and operate an ASR solution on the company’s infrastructure, adding an API and monitoring where needed.
Next step
Send a short description of your use case to receive a scoped proposal for diagnosis and implementation.
Let's assess your project
I reply with scope and a proposal.