DEV Community

#stt

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
NVIDIA Nemotron 3.5 Transcribe: One Offline Checkpoint for Prompted Transcription, Speakers, and Translation
madnessbrains_i profile
devs

NVIDIA Nemotron 3.5 Transcribe: One Offline Checkpoint for Prompted Transcription, Speakers, and Translation

#nvidia #asr #stt #windows
Comments
4 min read
Building an Open-Source Alternative to ElevenLabs and Deepgram: Introducing RagLeap Voice
ragleap profile

Building an Open-Source Alternative to ElevenLabs and Deepgram: Introducing RagLeap Voice

#showdev #stt #voicetech #tts
Comments
3 min read
Nemotron 3.5 Transcribe: One-GPU Promptable Offline STT for Multilingual Call Pipelines
madnessbrains_i profile
devs

Nemotron 3.5 Transcribe: One-GPU Promptable Offline STT for Multilingual Call Pipelines

#nvidia #stt #transcription #windows
Comments
4 min read
Azure LLM Speech 09-2026: 25 New Languages and 2 Faster Fast Transcription for Multilingual Call Pipelines
madnessbrains_i profile
devs

Azure LLM Speech 09-2026: 25 New Languages and 2 Faster Fast Transcription for Multilingual Call Pipelines

#azure #speech #stt #windows
Comments
5 min read
Microsoft’s MAI-Transcribe-2-Streaming and the 100 ms WASAPI Capture Budget
madnessbrains_i profile
devs

Microsoft’s MAI-Transcribe-2-Streaming and the 100 ms WASAPI Capture Budget

#windows #audio #stt #realtime
Comments
5 min read
NVIDIA Nemotron 3.5 Transcribe is offline on purpose: fitting a 4.3B-active speech LLM into a live Windows call path
madnessbrains_i profile
devs

NVIDIA Nemotron 3.5 Transcribe is offline on purpose: fitting a 4.3B-active speech LLM into a live Windows call path

#nvidia #stt #windows #realtime
Comments
6 min read
Realtime STT at $0.36/hour is not the hard part: turn-taking and the Windows capture path
madnessbrains_i profile
devs

Realtime STT at $0.36/hour is not the hard part: turn-taking and the Windows capture path

#windows #audio #stt #realtime
Comments
4 min read
Stop Wrestling with ASR: The Complete Guide to Gemini 3.5 Transcribe 🎙️
giom_v profile

Stop Wrestling with ASR: The Complete Guide to Gemini 3.5 Transcribe 🎙️

#ai #stt #tutorial
37
Comments
10 min read
Practical Techniques to Improve Faster-Whisper Recognition Accuracy — Use Recent Conversations, Not Dictionaries, for initial_prompt
orca_forge profile

Practical Techniques to Improve Faster-Whisper Recognition Accuracy — Use Recent Conversations, Not Dictionaries, for initial_prompt

#fasterwhisper #whisper #stt #ai
2
Comments
4 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.