ElevenLabs
Voice cloning, TTS, and STT from ElevenLabs
ElevenLabs is the voice-AI platform, text-to-speech with the closest to human-sounding output in the industry, voice cloning, sound-effect generation, and speech-to-text in one API. Seven actions cover the surface: Text to Speech (the workhorse, high-quality TTS with model and voice selection), Speech to Text (whisper-quality transcription), Clone Voice (Instant) (create a custom voice from a 30-second sample), Generate Sound Effect (short sound effects from text prompts), List Voices, Get Voice (full voice metadata), Get User Info (subscription state and quota). No triggers. The integration uses an ElevenLabs API key. Common patterns: a podcast workflow runs Speech to Text on every uploaded episode, summarises the transcript with an AI step, and pushes the summary to a Notion knowledge base; or a customer-success workflow uses Text to Speech with a cloned founder voice to generate personalized welcome audio for high-value new sign-ups.
Do anything ElevenLabs can do, from a workflow.
Every action accepts dynamic inputs from upstream nodes, whether that's an AI output, a form field, or a search result.
| Action | What it does |
|---|---|
| Instant Voice Clone | Trains a custom voice from a short audio sample (a few minutes ideal). Once trained, the voice ID is usable in Text to Speech for consistent narration. For brand-voice or character-voice production at scale. |
| Generate Sound Effect | Generates short audio effects from a text prompt ("door creak", "thunder", "applause"). Useful for video production workflows that need sound effects alongside generated narration. |
| Get ElevenLabs Account Info | Returns the connected account's details including remaining character quota for the current period. Pre-flight on bulk-narration batches to avoid mid-batch quota exhaustion. |
| Get Voice | Returns a voice's metadata — name, gender, age, accent, description. Useful for "show me the voice configuration before generating" workflows. |
| List Voices | Returns stock voices plus any custom-cloned voices for the account. Useful for voice-picker UIs at workflow setup or for inventorying available voice catalogs. |
| Speech to Text | Transcribes audio using ElevenLabs' speech recognition. While ElevenLabs is better known for TTS, their STT is competitive with Deepgram/AssemblyAI for specific use cases. Useful for unified ElevenLabs-only voice-agent workflows. |
| Text to Speech | Generates high-quality audio from text using ElevenLabs voices (stock or cloned). The premium-quality TTS option vs faster/cheaper alternatives — for broadcast-quality narration, audiobook production, or branded voice content. |
Pre-built ElevenLabs workflows.
Clone any recipe and customize it in one click. Every recipe is fully editable.
Three things worth knowing.
Tiny Command counts a run the moment a trigger fires. Filtering early means only matching events spend your usage budget.
Connect ElevenLabs once and every workflow on your account can use its triggers and actions. You don't have to re-auth per workflow.
Every ElevenLabs field shows up in the visual picker for downstream nodes. The raw payload is there for power users, optional for everyone else.
Questions about the ElevenLabs integration.
If we missed yours, ping support. We usually reply within an hour.
How do I connect ElevenLabs to Tiny Command?
What ElevenLabs triggers does Tiny Command support?
What ElevenLabs actions can I run from a workflow?
Is the ElevenLabs integration real-time?
Do I need to write code to use ElevenLabs with Tiny Command?
How much does the ElevenLabs integration cost?
More ai & ml apps people connect.
Same category as ElevenLabs, ordered by how often teams pair them. Hover the carousel to pause.
Do more with ElevenLabs.
Wire it to Slack, Notion, HubSpot, Stripe, or any of the other 438 apps in our catalog. Setup takes roughly two minutes. Free to try, no credit card.
