Vision AgentsStream
|
||||||
Related Products
|
||||||
About
Tunk.ai is a multilingual AI voice agent platform that enables businesses to build, deploy, and manage intelligent voice agents for customer interactions and business workflows. With its Anchor agent builder, businesses can create AI voice agents using prompts and connect them to telephony, APIs, CRMs, MCP servers, external tools, and business systems. Tunk.ai supports speech-to-text, text-to-speech, real-time voice conversations, SIP and telephony integrations, tool calling, function calling, and multiple AI and speech providers. Agents can use connected tools to retrieve information, perform actions, update systems, and automate workflows. Tunk.ai can automate customer support, sales, lead qualification, appointment scheduling, recruitment, healthcare workflows, collections, reminders, and contact-center operations. The platform supports multiple languages, customizable workflows, APIs, integrations, and scalable infrastructure for SMB and enterprise deployments.
|
About
Vision Agents is an open source Python framework for building low-latency voice and video AI agents with any model. It lets developers plug in LLM, speech, and vision models from more than 25 providers and ship real-time agents for telehealth, voice support, live coaching, video analysis, interactive avatars, security monitoring, sports commentary, and other multimodal applications. It is designed to help teams build agents that can listen, speak, see, process media, call tools, and respond in real time while running on Stream’s global edge network with sub-500ms latency. Developers can build a first agent in minutes, using a small Python setup with Gemini Realtime, OpenAI, Deepgram, ElevenLabs, Stream, or other supported providers. Vision Agents supports both real-time speech-to-speech models and custom STT/LLM/TTS pipelines, giving teams either the fastest path to a working voice agent or full control over speech recognition, language reasoning, text-to-speech, etc.
|
|||||
Platforms Supported
Windows
Mac
Linux
Cloud
On-Premises
iPhone
iPad
Android
Chromebook
|
Platforms Supported
Windows
Mac
Linux
Cloud
On-Premises
iPhone
iPad
Android
Chromebook
|
|||||
Audience
Organizations and businesses of all sizes, including SMBs, mid-market companies, and enterprises, can benefit from Tunk.ai. It is particularly suited for contact centers, BPOs, healthcare providers, BFSI and insurance companies, real estate, hospitality, recruitment firms, e-commerce businesses, sales and customer support teams, and organizations looking to automate repetitive voice-based workflows.
|
Audience
Developers that need to build low-latency voice and video AI agents using interchangeable speech, vision, and language models
|
|||||
Support
Phone Support
24/7 Live Support
Online
|
Support
Phone Support
24/7 Live Support
Online
|
|||||
API
Offers API
|
API
Offers API
|
|||||
Screenshots and Videos |
Screenshots and Videos |
|||||
Pricing
$0.05 per minute
Free Version
Free Trial
|
Pricing
Free
Free Version
Free Trial
|
|||||
Reviews/
|
Reviews/
|
|||||
Training
Documentation
Webinars
Live Online
In Person
|
Training
Documentation
Webinars
Live Online
In Person
|
|||||
Company InformationTunk.ai
Founded: 2024
India
tunk.ai
|
Company InformationStream
United States
visionagents.ai/
|
|||||
Alternatives |
Alternatives |
|||||
|
|
||||||
|
|
||||||
|
|
||||||
Categories |
Categories |
|||||
Integrations
Amazon Bedrock
Amazon Nova
Amazon Polly
Anama
AssemblyAI
Claude
Deepgram
Docker
ElevenLabs
GPT-5
|
Integrations
Amazon Bedrock
Amazon Nova
Amazon Polly
Anama
AssemblyAI
Claude
Deepgram
Docker
ElevenLabs
GPT-5
|
|||||
|
|
|