✍️Writing & Content35🎨Image Generation43🎬Video & Animation76🎵Audio & Music67💬Chatbots & Assistants58💻Coding & Development284📈Marketing & SEO87⚡Productivity218🎯Design & UI/UX71📊Data & Analytics69📚Education & Research30💼Business & Finance75🏥Healthcare & Wellness18🔍Search & Knowledge17🤖AI Agent Infrastructure121🛡️AI Security & Testing17🧊3D & Spatial21🔎SEO Tools34🏡Real Estate4🗃️Data Extraction32🧠ADHD & Focus Tools9
💡

Complete Your AI Agent Stack

Spix users also rely on these tools to enhance their workflow:

1Password

Try Free

Secrets and credential manager

Keep API keys and .env secrets out of your repo

$2.99/mo+Learn more →

Consensus

Try Free

AI search across 200M research papers

Source real evidence behind your analysis

Free tier, $8.99/mo+Learn more →

Gamma

Try Free

AI presentation builder

Turn ideas into polished decks instantly

Free tier, $10/mo+Learn more →

💰 Affiliate disclosure: We may earn a commission if you sign up through these links at no extra cost to you.

Listed in AI Agent Infrastructure with 124 other toolsPart of 1554+ curated AI tools on AISO
Spix logo

Spix

Voice, SMS and email infrastructure for AI agents — MCP-native, ~500ms call latency, CLI-first

0
freemiumSandbox is $0/month for testing, with 1,000 email events and no usage credits or concurrent calls. Agent is $20/month with 500 usage credits, 2 concurrent calls and email support. Operator is $99/month with 5,000 credits, 10 concurrent calls and 8-hour SLA support. Fleet is $299/month for high-volume operations with dedicated support. Credit packs run from $10 for 1,000 credits ($0.0100 each) to $800 for 100,000 credits ($0.0080 each). Add-ons: US local number $3/month, toll-free $5/month, extra inbox $2/month.View full pricing →

Visit Spix

https://spix.sh

💰 View Detailed Pricing →Try Spix →

About Spix

Spix gives an AI agent a phone number, an inbox and a voice — the communications primitives that most agent frameworks leave as an exercise for the developer. Install once and the agent can place and receive voice calls, send and receive SMS, and send email, all driven from the CLI or over MCP. The voice pipeline is the substantial part: outbound and inbound AI calls run through real-time transcription and LLM conversation logic with speech synthesis at roughly 500ms end-to-end latency, and calls are driven by reusable playbooks rather than ad-hoc prompts, so a call is a repeatable artefact. Installation is a single curl script, with one-click install prompts published for Claude Code, Codex, OpenClaw and Hermes Agent, which is a clear signal about who the product is for. Billing is a hybrid that suits agent workloads: monthly plans set concurrency limits, email-event allowances and a bundled credit allocation, while usage beyond that draws on credit packs priced from $0.0100 down to $0.0088 per credit at volume. Phone numbers and extra inboxes are add-ons at $3-$5/month. A free Sandbox tier lets you test the voice path before spending anything.

Key Features

✓Outbound and inbound AI voice calls at roughly 500ms end-to-end latency
✓SMS and email from the same install
✓MCP-native, plus a CLI for direct use
✓Reusable call playbooks rather than ad-hoc prompts
✓One-command curl install with published prompts for Claude Code, Codex, OpenClaw and Hermes
✓Real-time transcription plus LLM conversation logic in the speech pipeline
✓Phone numbers and extra inboxes as low-cost add-ons

Spix Pros & Cons

✅ Pros

  • +Covers voice, SMS and email in one install instead of stitching three vendors together
  • +MCP-native means any compatible agent gets telephony without custom glue code
  • +Free sandbox lets you validate the voice pipeline before committing
  • +Volume credit packs make high-call-count workloads meaningfully cheaper
  • +Playbooks turn calls into versioned artefacts rather than one-off prompts

⚠️ Cons

  • −Plan credits plus credit packs plus per-number add-ons make total cost hard to forecast
  • −2 concurrent calls on the $20 tier is very limiting for anything beyond testing
  • −Giving an autonomous agent outbound calling capability carries obvious compliance risk
  • −Documentation-first, CLI-first design assumes a developer operator

Who Is Spix Best For?

👤Developers building voice agents who do not want to assemble a telephony stack
👤Teams running Claude Code, Codex or OpenClaw agents that need to reach people
👤Anyone prototyping outbound calling workflows with an LLM in the loop

Tags

ai-agentsvoice-agentsmcpsmsemailcli
🏷️

Is this your tool?

Claim your listing to get a Featured badge, edit your description, and stand out from competitors. All plans include a permanent dofollow backlink to your site.

Claim Now →

ChatGPT already recommends Spix. Does it recommend yours?

If you're building in AI Agent Infrastructure, run a free AI-visibility scan on your own product — we ask ChatGPT across 5 prompt angles and score how often you get named. ~30 seconds, no signup, no card.

Scan my tool — free →or scan Spix instead

Stay updated on AI Agent Infrastructure tools — join our weekly newsletter

One concise email with fresh launches, trending picks, and featured standouts.

Agent connectivity: not yet verified