home / skills / openclaw / skills / slybroadcast-voicemail

slybroadcast-voicemail skill

safe

/skills/danielfoch/slybroadcast-voicemail

This skill helps you send Slybroadcast voicemail campaigns and generate AI voices from text, with flexible playback and scheduling.

npx playbooks add skill openclaw/skills --skill slybroadcast-voicemail

Review the files below or copy the command above to add this skill to your agents.

Files (2)

SKILL.md

2.6 KB

---
name: slybroadcast-voicemail
description: Send Slybroadcast ringless voicemail campaigns from OpenClaw/LLMs using CLI or MCP, including AI voice generation (ElevenLabs or generic HTTP voice API) and campaign controls.
---

# Slybroadcast Voicemail

Use this skill when the user wants to send one or many voicemail drops with Slybroadcast and optionally generate a voice recording from text.

## Prerequisites

Required environment variables:

- `SLYBROADCAST_UID` (or `SLYBROADCAST_EMAIL` fallback)
- `SLYBROADCAST_PASSWORD`
- `SLYBROADCAST_DEFAULT_CALLER_ID` (or pass caller id explicitly)

For local-file or AI-generated audio, also set:

- `SLYBROADCAST_PUBLIC_AUDIO_BASE_URL`
- `SLYBROADCAST_AUDIO_STAGING_DIR`

For ElevenLabs voice generation:

- `ELEVENLABS_API_KEY`
- `ELEVENLABS_TTS_VOICE_ID`

## CLI Commands

Run direct commands:

```bash
npm --workspace @fub/slybroadcast-voicemail run dev:cli -- send --help
```

Common examples:

1. Existing account recording title:

```bash
npm --workspace @fub/slybroadcast-voicemail run dev:cli -- send \
  --to "16173999981,16173999982" \
  --record-audio "My First Voice Message" \
  --caller-id "16173999980" \
  --campaign-name "Follow-up" \
  --schedule-at "now"
```

2. Public audio URL:

```bash
npm --workspace @fub/slybroadcast-voicemail run dev:cli -- send \
  --to "16173999981" \
  --audio-url "https://example.com/voicemail.mp3" \
  --audio-type mp3 \
  --caller-id "16173999980"
```

3. ElevenLabs text-to-voice + send:

```bash
npm --workspace @fub/slybroadcast-voicemail run dev:cli -- send \
  --to "16173999981" \
  --ai-text "Hi, this is your appointment reminder for tomorrow at 3 PM." \
  --ai-provider elevenlabs \
  --caller-id "16173999980"
```

4. Uploaded list on Slybroadcast platform:

```bash
npm --workspace @fub/slybroadcast-voicemail run dev:cli -- send \
  --list-id 94454 \
  --record-audio "My First Voice Message" \
  --caller-id "16173999980"
```

## MCP Tools

Start the MCP server:

```bash
npm --workspace @fub/slybroadcast-voicemail run dev:mcp
```

Tool names:

- `slybroadcast_voicemail_send`
- `slybroadcast_audio_list`
- `slybroadcast_phone_list`
- `slybroadcast_campaign_status`
- `slybroadcast_campaign_results`
- `slybroadcast_campaign_control`
- `slybroadcast_voice_generate`

## Notes

- Slybroadcast API delivery times are interpreted in Eastern Time and use 24-hour format (`YYYY-MM-DD HH:MM:SS`).
- Use one audio source per campaign request: account recording title, system audio file, public URL, local file, or AI text.
- Local and AI-generated files are staged first and must be publicly reachable for Slybroadcast to fetch.

Overview

This skill sends ringless voicemail campaigns through Slybroadcast from CLI or the MCP server and can generate AI voices via ElevenLabs or a generic HTTP voice API. It supports single or bulk drops, campaign scheduling, caller ID control, and staging of local or AI-generated audio for Slybroadcast to fetch. It is designed for automation from OpenClaw/LLMs and programmatic workflows.

How this skill works

The skill accepts an audio source per campaign: existing account recording, public URL, staged local file, or AI-generated text-to-speech. Local or AI-generated files are uploaded to a public staging URL so Slybroadcast can retrieve them. You can run commands via the CLI or call MCP tools to create, control, and monitor campaigns and results.

When to use it

Send appointment reminders, promotions, or notifications without placing live calls
Deliver large batches of ringless voicemail drops with scheduling and caller ID control
Automate voicemail creation from LLMs or generate AI voice messages on demand
Integrate voicemail campaigns into CRM workflows or notification systems
Test voicemail delivery and campaign performance programmatically

Best practices

Provide only one audio source per campaign request to avoid conflicts
Ensure environment variables for Slybroadcast credentials, staging URLs, and TTS keys are set before sending
Stage local or AI-generated audio to a publicly reachable URL so Slybroadcast can fetch it
Use campaign scheduling in Eastern Time with 24-hour format (YYYY-MM-DD HH:MM:SS) to avoid timing errors
Monitor campaign status and results via MCP tools and handle retries for failed drops

Example use cases

Send a same-day appointment reminder generated from AI TTS and scheduled for immediate delivery
Deliver a promotional voicemail to a uploaded contact list on the Slybroadcast platform
Use a public MP3 hosted on your CDN to run a short campaign without uploading files
Bulk-send follow-up voicemails with caller ID set to your verified number and track delivery via campaign results
Generate personalized messages per contact using an LLM to craft the script and ElevenLabs to render voice

FAQ

What environment variables are required?

You must set SLYBROADCAST_UID (or SLYBROADCAST_EMAIL), SLYBROADCAST_PASSWORD, and SLYBROADCAST_DEFAULT_CALLER_ID. For staging or AI voices also set SLYBROADCAST_PUBLIC_AUDIO_BASE_URL and SLYBROADCAST_AUDIO_STAGING_DIR; for ElevenLabs set ELEVENLABS_API_KEY and ELEVENLABS_TTS_VOICE_ID.

Can I use more than one audio source per campaign?

No. Use exactly one audio source per campaign request: account recording title, system audio file, public URL, local staged file, or AI-generated text.

How do I run it programmatically?

Start the MCP server and call the provided tools (e.g., slybroadcast_voicemail_send, slybroadcast_campaign_status, slybroadcast_voice_generate) to create, control, and monitor campaigns.