Skip to content
Notis

Keep preferred pronunciations in one dictionary

Turn pronunciation corrections into reusable rules so future generated speech can say important terms consistently.

Trigger

New Message Received

Triggered when your bot receives a new message in a private chat, group, or supergroup. To receive every message in a group, Privacy Mode must be disabled for the bot in BotFather.

Action

Add rules to the pronunciation dictionary

Adds one or more custom pronunciation rules (alias or phoneme) to an existing pronunciation dictionary.

Why this helps

The same name or specialist term may be corrected repeatedly across audio work.

  • Reuse pronunciation corrections in later speech projects.
  • Reduce repeated manual fixes to common terms.
  • Keep brand and people names more consistent.

Setup

Build it in a few focused steps.

  • 1Connect Telegram and ElevenLabs to Notis once through the portal.
  • 2Create an automation in the portal or tell Notis the outcome you want.
  • 3Ask Notis to interpret Telegram pronunciation requests and add the stated alias or phoneme rule to the existing ElevenLabs pronunciation dictionary.
  • 4Choose New Message Received as the trigger and select a channel for run reports.
  • 5Test with one approved pronunciation correction and review the dictionary change.

Questions about this workflow

Does this create a dictionary?

No. This action adds rules to an existing pronunciation dictionary, so an existing dictionary is required.

Can I provide a simple spelling hint?

Describe the desired pronunciation clearly in your Telegram message and ask Notis to translate it into an appropriate rule.

When this happens · Trigger

Do this · Action

Supported Triggers and Actions

Notis builds workflows that link Telegram to Elevenlabs. A trigger fires from one place; an action lands in another.

Telegram triggers

Elevenlabs actions

Recurring trigger

Notis starts this workflow on a schedule, such as daily, weekly, or during business hours.

TriggerScheduled

Add a pronunciation dictionary from file

Adds a new pronunciation dictionary from a lexicon file to improve speech synthesis accuracy.

ActionInstant

Webhook trigger

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

TriggerInstant

Add new project with attributes

Use to create a new elevenlabs project for text-to-speech synthesis (e.g., audiobooks); a project `name` is required by the api for creation, and content can be initialized using `from url` or `from document`.

ActionInstant

New Message Received

Triggered when your bot receives a new message in a private chat, group, or supergroup. To receive every message in a group, Privacy Mode must be disabled for the bot in BotFather.

TriggerInstant

Add rules to the pronunciation dictionary

Adds one or more custom pronunciation rules (alias or phoneme) to an existing pronunciation dictionary.

ActionInstant

New Channel Post

Triggered when a new post is published to a channel where your bot is an administrator.

TriggerInstant

Add sharing voice

Adds an existing, shareable voice to a specified user's elevenlabs account library under a new custom name, requiring the user's public id and the voice id.

ActionInstant

Callback Query Received

Triggered when a user taps an inline keyboard button attached to one of your bot's messages.

TriggerInstant

Add a voice

Adds a custom voice, requiring a `name` and a `files` list with at least one audio sample, to initiate cloning; returns `voice id` but voice is not immediately usable for synthesis.

ActionInstant

Message Edited

Triggered when a message in a chat your bot can see is edited by its sender.

TriggerInstant

Convert chapter to audio

Converts the textual content of a chapter, identified by `chapter id` within a `project id`, into audio format.

ActionInstant

New Chat Member

Triggered when a new member joins a group or supergroup the bot belongs to, including when the bot itself is added.

TriggerInstant

Convert a project

Converts an existing elevenlabs studio project, including all its chapters and using its configured settings and voices, into speech.

ActionInstant

Create a previously generated voice

Finalizes the creation of a voice using its `generated voice id` from a previous generation step by assigning a name, description, and optional labels.

ActionInstant

Connect any two apps with Notis in the middle.

Telegram and Elevenlabs, or any other 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.