Skip to content
Notis

Know Who Said What in Every Lead Call

Speaker-aware transcripts turn a messy recording into a practical reference for decisions and follow-up.

Trigger

Webhook received

Notis starts this workflow when an external tool or custom backend sends an HTTP request.

Action

Speech to Text

Transcribe an audio or video file from a URL with ElevenLabs Scribe — 90+ languages, word timestamps, speaker diarization, audio-event tagging, optional entity detection and keyterm biasing.

Why this helps

Without speaker labels, founders must reconstruct ownership of questions, objections, and promises by listening again.

  • Clarifies commitments by speaker
  • Speeds review of multi-person calls
  • Improves follow-up accuracy

Setup

Build it in a few focused steps.

  • 1Connect The Org and ElevenLabs to Notis once in the portal.
  • 2Create the automation in the portal or ask Notis to create it conversationally.
  • 3Use this instruction: When a multi-person The Org lead recording arrives, transcribe it with ElevenLabs Speech to Text and return speaker labels, timestamps, and a short list of commitments by person.
  • 4Select an incoming webhook trigger, choose a reporting channel, and test with one real call.

Questions about this workflow

Does it support multiple speakers?

Yes. ElevenLabs Speech to Text can return speaker diarization for supported recordings.

Can the result include commitments?

Yes. Ask Notis to summarize commitments after receiving the transcript.

When this happens · Trigger

Do this · Action

Supported Triggers and Actions

Notis builds workflows that link The Org to ElevenLabs. A trigger fires from one place; an action lands in another.

The Org triggers

ElevenLabs actions

No triggers available yet

Voice Isolator

Remove background noise, music and ambient sounds from a recording, returning clean studio-quality speech (MP3, base64).

ActionInstant

Voice Changer

Transform a recording into a different ElevenLabs voice while preserving the original emotion, timing and delivery (MP3, base64 output).

ActionInstant

Forced Alignment

Align a known transcript to its audio recording, returning precise word-level timestamps (subtitles, audiobook timings, karaoke).

ActionInstant

List Voices

List the ElevenLabs voices available to this account (voice_id, name, category, labels, preview_url).

ActionInstant

Speech to Text

Transcribe an audio or video file from a URL with ElevenLabs Scribe — 90+ languages, word timestamps, speaker diarization, audio-event tagging, optional entity detection and keyterm biasing.

ActionInstant

Music Generation

Generate studio-grade music (MP3) in any style from a natural language prompt with Eleven Music — vocals or instrumental, commercial-use cleared.

ActionInstant

Connect any two apps with Notis in the middle.

Not just The Org and ElevenLabs. Any combination from 1,000+ integrations.

When this happens · Trigger

Do this · Action

Save your first hour today.

7-day trial of any paid plan, with 20$ of usage included.
No card. Works with personal or business ElevenLabs.