Voice Synthesis
Give your n8n workflows a voice
Seamlessly hear responses from your LLM agents with native Text-to-Speech integration. Perfect for hands-free operations while commuting or multitasking.
Typing and reading text isn't always convenient, especially when you are multitasking, driving, or simply prefer an auditory experience. Voice Synthesis in Tellflow bridges this gap by directly reading out the responses from your n8n workflows using advanced TTS models. By natively integrating with providers like ElevenLabs, Tellflow delivers podcast-quality speech in real-time.
The integration is incredibly smooth. By leveraging the Tellflow n8n node, you can define exactly which part of your workflow's output should be synthesized and which part should remain as text. The mobile app decodes the audio streams on the fly, allowing for near-instant playback. It even supports background audio, so your AI agent can keep talking while you switch to other apps.
Core Capabilities
Deep integration directly into your mobile workflows.
ElevenLabs Support
Native integration enabling ultra-realistic human voices for your assistant.
Background Playback
Listen to long AI-generated answers even when the app is minimized.
Multi-language
Automatically detect and synthesize speech across multiple languages.
Experience n8n on mobile
Join thousands of developers who are scaling their AI operations from their pocket with Tellflow.