Famulor - Ultra-fast AI assistant for calls and live chat
by•
Famulor is an ultra-fast AI assistant for calls, live chat, WhatsApp and Meta Messenger. It helps businesses never miss a lead, qualify callers, and support customers 24/7 with human-like conversations. Hosted in the EU and GDPR-compliant, Famulor combines intelligent telephony, chat automation and analytics in one platform so you can go live in minutes, no code needed.
Replies
Famulor sounds really useful, especially being available 24/7 and GDPR-compliant. The 250+ integrations and Activepieces support make it feel ready for real business use.
How does it handle calls when someone speaks quickly or with a strong accent?
@ciril_raj Thanks Ciril! Fast speech and strong accents are exactly where our latest speech updates help most.
We upgraded our transcription stack in two ways:
ElevenLabs Scribe v2 (Pipeline Mode): sharper accuracy, better punctuation, and faster transcription — especially helpful for complex dialogue and noisy calls.
Deepgram auto-migration Nova-2 → Nova-3: higher accuracy, improved noise handling, and quicker responses for all Deepgram-based assistants.
On live calls, we also handle tough audio with practical safeguards: streaming partial transcripts + turn detection, and confidence-based fallback (e.g., asking to repeat/confirm key details like names, emails, numbers) so the assistant doesn’t “guess” when audio is unclear.
If you want, share your main call languages/regions — we can suggest the best STT setup and a couple of tuning tips for your use case.
This release brings upgrades to voice quality, transcription accuracy, and usability across the platform — along with a few handy workflow improvements.
🗣️ Cartesia Sonic 3 (TTS) for Pipeline & Dualplex
Introducing Cartesia Sonic 3, our newest high-fidelity TTS engine with voice cloning support and advanced emotion control.
🎭 Toggle SAML tags to adjust tone, emotion, and intensity in your AI’s voice.
🎤 Clone and fine-tune voices directly within your assistants for natural, expressive conversations.
✍️ ElevenLabs Scribe v2 Transcriber
We’ve added Scribe v2, a cutting-edge transcription model from ElevenLabs, now available in Pipeline Mode.
Expect sharper accuracy, better punctuation, and faster transcription speeds — perfect for complex dialogues and noisy environments.
🎙️ Record Voice Samples in-App
You can now record voice samples directly inside the platform for cloning.
No need to upload pre-recorded files — just hit record, speak, and your voice sample will be ready to use in seconds.
🔁 Deepgram Nova-3 Migration
All assistants using Deepgram have been automatically upgraded from Nova-2 → Nova-3, bringing:
Higher transcription accuracy
Better noise handling
Faster response times
🌐 Web Widget Preview Sharing
You can now copy a shareable preview URL of your web widget — no need to embed it on a website first.
Perfect for demoing widgets to clients or sharing with your team during testing.
🔄 Bulk Resend Webhooks
Quickly resend multiple webhooks for past calls in one action.
Ideal for syncing historical data, debugging integrations, or recovering missed events.
These updates make your assistants more powerful, expressive, and developer-friendly — with the latest models and smarter workflow tools across the board.