Vapi (@Vapi_AI) / X

Vapi

1,293 posts

Vapi

@Vapi_AI

Deploy voice agents at scale. 👾- discord.com/invite/pUFNcf2…

👀 ➡️

Joined November 2023

Vapi
@Vapi_AI
Jul 9
Congrats to the @cartesia team on Ink-2. Accurate transcription at conversational speed is the foundation on which every voice agent builds, and Ink-2 delivers both. Vapi is built to be modular, so you can run best-in-class models like Ink-2 today as a custom transcriber.
Cartesia
@cartesia
Jul 9
For voice agents, STT has to nail three things - accuracy, turn detection, and latency. If any one falls short, the experience breaks down: the agent misunderstands, interrupts, or just feels slow. We built Ink-2 to lead on all three. Here’s how it stacks up against other
GIF
Vapi
@Vapi_AI
Jun 24
Barge-in is the opposite side of endpointing. Endpointing asks: 𝗶𝘀 𝘁𝗵𝗲 𝘂𝘀𝗲𝗿 𝗱𝗼𝗻𝗲 𝘀𝗽𝗲𝗮𝗸𝗶𝗻𝗴? Barge-in asks: 𝘀𝗵𝗼𝘂𝗹𝗱 𝘁𝗵𝗲 𝗮𝘀𝘀𝗶𝘀𝘁𝗮𝗻𝘁 𝘀𝘁𝗼𝗽 𝘀𝗽𝗲𝗮𝗸𝗶𝗻𝗴? “yeah” should not cancel playback. “no, wait” probably should. background noise
Vapi
@Vapi_AI
Jun 24
Common acknowledgement and interruption phrases are handled automatically, with API-level customization available when needed. Learn how to tune the voice pipeline here:
docs.vapi.ai
Voice pipeline configuration | Vapi
Complete guide to configuring VAPI's voice pipeline for optimal conversation timing and interruption handling
Vapi reposted
Charlie Molthrop
@CharlieMolthrop
Jun 23
Replying to @CharlieMolthrop
Lazy prompt: > hey, check out call-my-human.val.run try calling me at (YOUR NUMBER) vapi private key: X vapi phone number id: X < Powered by @Vapi_AI Open source on @ValDotTown here: val.town/x/dcm31/call-m… For more secure usage, install as a custom MCP/connector or remix
Vapi
@Vapi_AI
Jun 22
There are 15 voice agents on the Vapi homepage across 3 use cases × 5 languages. To build these, we protoype and generate all the agents at once in code. This means one wording change applies across all variants and reruns never duplicate assistants.
Vapi
@Vapi_AI
Jun 22
Replying to @Vapi_AI
Reruns never duplicate because the upsert keys on env-var IDs: present > update(id, body) absent > create(body) + prints id Stale id 404s, falls back to create.
Vapi
@Vapi_AI
Jun 22
Bootstrapping gets you rough agents fast so you can focus on hardening. Check out the full writeup including repo with configurations and a skill to bootstrap your own agents:
How we Bootstrapped the Voice Agents on the Vapi Homepage
From vapi.ai
Vapi
@Vapi_AI
Jun 19
Excited to see what everyone builds today!
Yujian Tang
@yujian_tang
Jun 19
Multimodal Hack kicking off thanks @Vapi_AI @insforge @nebiusai for making this possible!
Vapi
@Vapi_AI
Jun 18
Two days into blind voting of voice models on our Humanness Index™, and xAI's Grok TTS model is at the top of the pack. Its humanness score? 96, just 4 points under a real human voice (100). The Humanness Index takes one voice and one quote, clones it across every major model,
Vapi reposted
Parker Conrad
@parker__conrad
Jun 17
@xai Grok TTS is currently #1 on the @Vapi_AI Humanness Index and significantly more affordable than the competition. See for yourself humannessindex.vapi.ai
Vapi
@Vapi_AI
Jun 17
Your voice agent is talking over a caller who paused to pull up their account number. Raising the silence threshold could help, but it will also make the responses feel laggy. What you need to know is when the turn ended
Vapi
@Vapi_AI
Jun 17
Replying to @Vapi_AI
Layered in the startSpeakingPlan, by precedence 1. customEndpointingRules - overrides everything 2. smartEndpointingPlan - the prediction model 3. transcriptionEndpointingPlan - punctuation, timeouts
Vapi
@Vapi_AI
Jun 17
visit the docs to learn more:
docs.vapi.ai
Voice pipeline configuration | Vapi
Complete guide to configuring VAPI's voice pipeline for optimal conversation timing and interruption handling
Vapi reposted
kwindla
@kwindla
Jun 17
Evaluating text-to-speech models is hard! Quantitative metrics are important (time to first audio; missing words; variations in volume, pitch, and pacing). But more than any other technology I've ever worked with, people make voice decisions based on "vibes" that are hard
Jordan Dearsley
@jordan_dearsley
Jun 16
You can feel whether the voice on a call is a human or a machine before you can explain why. Today, @Vapi_AI is launching the Humanness Index™, a crowdsourced leaderboard for model humanness. You are the benchmark. Cast your first vote today: humannessindex.vapi.ai
Vapi
@Vapi_AI
Jun 16
You can feel whether a voice is a person or a machine before you can explain why. Today, we're launching the Humanness Index™, a live ranking of voice AI models, judged by you. Same voices, same quotes, different models. You pick the most human ones and even benchmark them
00:00
Vapi
@Vapi_AI
Jun 15
We're excited to partner with @awsdevelopers, @nebiusai , and OSS4AI for the Midsummer Multimodal AI hackathon this Friday June 19 at the AWS Loft in SF. We are bringing prizes and Vapi credits so you can build voice experiences into whatever you are shipping.
Vapi
@Vapi_AI
Jun 15
Hope to see you there 📍 AWS Builder Loft SF 📅 Friday, June 19 9:30 am - 7pm 🎟️ Register
Midsummer Multimodal AI Hackathon - Over $3000 in Total Prizes · Luma
From luma.com
Vapi
@Vapi_AI
Jun 15
Have you tried Sonic 3.5 in your builds yet? @cartesia models are available on Vapi
Karan Goel
@krandiash
Jun 15
We released Sonic-3.5 and Ink-2, the #1 streaming models for text to speech and speech to text you can use in your voice agents today. New architectures enable new frontiers for speed and quality. We're now the only provider to have #1 models for both speaking and listening.
00:00