Build and deploy LLM agents just using natural language! AutoAgent is the Fully-Automated & Zero-CodeLLM Agent Framework that let's you create and deploy LLM agents using just natural language. Key Features: Agentic-RAG – Built-in self-managing vector database,
@sumanth_077
-
Microsoft Open Sources VibeVoice-ASR for 60-Minute Speech Processing
By
–
If you found it useful, reshare it with your network Follow me → @Sumanth_077 for more insights and tutorials on AI Engineering! nitter.net/Sumanth_077/status/204… Sumanth (@Sumanth_077) Microsoft just fixed a major speech recognition problem! They open sourced VibeVoice-ASR, a speech-to-text model that processes 60 minutes of audio in a single pass. Here's the problem with most ASR models. They slice audio into short chunks, usually 30 seconds or less. Process each chunk separately. Lose speaker context between segments. You get disconnected transcripts that can't track who said what across a full meeting. VibeVoice-ASR handles 60 minutes of continuous audio without chunking. The model maintains global context across the entire hour. The output is structured. Who spoke, when they spoke, what they said. Speaker diarization, timestamps, and transcription all in one pass. Key features: • 60-minute single-pass processing without chunking audio • Structured output: speaker labels, timestamps, and content combined • Customized hotwords: provide specific names or technical terms to improve accuracy • Multilingual support: 50+ languages • Joint ASR, diarization, and timestamping in one model The model is 7B parameters. Available on Hugging Face with finetuning code included. I've shared the repo link in the comments! — https://nitter.net/Sumanth_077/status/2041157100840051111#m
→ View original post on X — @sumanth_077, 2026-04-06 14:14 UTC
-
Microsoft Shares VibeVoice GitHub Repository
By
–
Github Repo: github.com/microsoft/VibeVoi… [Translated from EN to English]
→ View original post on X — @sumanth_077, 2026-04-06 14:12 UTC
-
Microsoft Open Sources VibeVoice-ASR for 60-Minute Speech Recognition
By
–
Microsoft just fixed a major speech recognition problem! They open sourced VibeVoice-ASR, a speech-to-text model that processes 60 minutes of audio in a single pass. Here's the problem with most ASR models. They slice audio into short chunks, usually 30 seconds or less. Process each chunk separately. Lose speaker context between segments. You get disconnected transcripts that can't track who said what across a full meeting. VibeVoice-ASR handles 60 minutes of continuous audio without chunking. The model maintains global context across the entire hour. The output is structured. Who spoke, when they spoke, what they said. Speaker diarization, timestamps, and transcription all in one pass. Key features: • 60-minute single-pass processing without chunking audio • Structured output: speaker labels, timestamps, and content combined • Customized hotwords: provide specific names or technical terms to improve accuracy • Multilingual support: 50+ languages • Joint ASR, diarization, and timestamping in one model The model is 7B parameters. Available on Hugging Face with finetuning code included. I've shared the repo link in the comments!
→ View original post on X — @sumanth_077, 2026-04-06 14:12 UTC
-
Production-Scale Testing Enables Real Adversarial AI Validation
By
–
Agreed on the adversarial concern, but the economics here enable production-scale testing which is where real adversarial validation happens
-
Modulate’s Velma: Real-Time Deepfake Voice Detection API
By
–
If you found it useful, reshare it with your network Follow me → @Sumanth_077 for more insights and tutorials on AI Engineering! nitter.net/Sumanth_077/status/204… Sumanth (@Sumanth_077) Massive breakthrough in voice deepfake detection! @modulate_ai just released a deepfake detection API that topped @huggingface's leaderboard at 98.9% accuracy. Here's the problem with how most companies handle deepfake detection. They check the first 10 seconds of a call. If it passes, they assume the whole call is clean. Gate check. One scan. Done. Fraudsters know this. So they open the call with a real voice. Their own voice, a colleague, a quick recording. Pass the check. Then switch to the AI-generated clone mid-call. The system already gave them the green light. They're through. The fix is obvious. Monitor the entire call. Not just the opening. Not random spot checks. Every segment, continuously, in real-time. But that was too expensive. Until now. Velma is Modulate's real-time and batch deepfake detection API. Here's what changed. • Real-time streaming detection. Analyzes audio every 2 seconds during live calls. Catches mid-call voice switches instantly. • 120x cheaper than competitors. $0.25 per hour instead of $30-150. Now you can actually afford to monitor full conversations instead of spot-checking. • Only needs 2.5 seconds of audio. Faster detection, works with short segments. • 98.9% accuracy, ranked first on HuggingFace. Lower error rate than models 10x larger. First 1000 API credits are free. I've shared the link in the replies! — https://nitter.net/Sumanth_077/status/2040793953927311527#m
→ View original post on X — @sumanth_077, 2026-04-05 14:12 UTC
-
Checkout Modulate Deepfake Detection API
By
–
Checkout Modulate: modulate.ai/api/deepfake-det…
→ View original post on X — @sumanth_077, 2026-04-05 14:09 UTC
-
Modulate’s Velma API Achieves 98.9% Deepfake Detection Accuracy
By
–
Massive breakthrough in voice deepfake detection! @modulate_ai just released a deepfake detection API that topped @huggingface's leaderboard at 98.9% accuracy. Here's the problem with how most companies handle deepfake detection. They check the first 10 seconds of a call. If it passes, they assume the whole call is clean. Gate check. One scan. Done. Fraudsters know this. So they open the call with a real voice. Their own voice, a colleague, a quick recording. Pass the check. Then switch to the AI-generated clone mid-call. The system already gave them the green light. They're through. The fix is obvious. Monitor the entire call. Not just the opening. Not random spot checks. Every segment, continuously, in real-time. But that was too expensive. Until now. Velma is Modulate's real-time and batch deepfake detection API. Here's what changed. • Real-time streaming detection. Analyzes audio every 2 seconds during live calls. Catches mid-call voice switches instantly. • 120x cheaper than competitors. $0.25 per hour instead of $30-150. Now you can actually afford to monitor full conversations instead of spot-checking. • Only needs 2.5 seconds of audio. Faster detection, works with short segments. • 98.9% accuracy, ranked first on HuggingFace. Lower error rate than models 10x larger. First 1000 API credits are free. I've shared the link in the replies!
→ View original post on X — @sumanth_077, 2026-04-05 14:09 UTC
-
VoxCPM: Open-Source Voice Cloning Without Tokenization
By
–
If you found it useful, reshare it with your network Follow me → @Sumanth_077 for more insights and tutorials on AI Engineering! nitter.net/Sumanth_077/status/204… Sumanth (@Sumanth_077) Clone a human voice in real time without tokenization! VoxCPM is an open-source text-to-speech system that models speech in continuous space instead of discrete tokens. Most TTS systems convert speech to discrete tokens before generation. This quantization creates a fundamental trade-off: tokens provide stability but lose acoustic details like breath, vocal texture, and subtle articulation. VoxCPM skips tokenization entirely. It models speech directly in continuous space using an end-to-end diffusion autoregressive architecture built on MiniCPM-4. The system uses hierarchical language modeling with two specialized components: a Text-Semantic Language Model that captures high-level prosody and structure, and a Residual Acoustic Model that recovers fine-grained acoustic details. This separation eliminates dependency on external speech tokenizers and prevents error accumulation from multi-stage pipelines. Two flagship capabilities: 1. Context-aware speech generation: The model comprehends text to infer appropriate prosody and speaking style. Explanations slow down naturally, emphasis appears in the right places, questions sound like questions. 2. Zero-shot voice cloning: With just 3-10 seconds of reference audio, it replicates speaker timbre, accent, emotional tone, rhythm, and pacing. Key features: • Tokenizer-free architecture with continuous speech modeling • Context-aware prosody generation without manual tuning • Zero-shot voice cloning from short reference audio • Streaming synthesis support for real-time applications • SFT and LoRA fine-tuning support It's 100% open source Link to the GitHub repo in the comments! — https://nitter.net/Sumanth_077/status/2040055394958286903#m
→ View original post on X — @sumanth_077, 2026-04-03 13:15 UTC
-
VoxCPM GitHub Repository Released
By
–
Github Repo: github.com/OpenBMB/VoxCPM
→ View original post on X — @sumanth_077, 2026-04-03 13:14 UTC