SpeechifyAI n8n Node

This is an n8n community node. It lets you use Speechify's text-to-speech API in your n8n workflows.

Speechify provides high-quality, low-latency text-to-speech generation and a catalog of voices, via a REST API at https://api.speechify.ai.

n8n is a fair-code licensed workflow automation platform.

Installation Operations Credentials Compatibility Usage Resources Version history

Installation

Follow the installation guide in the n8n community nodes documentation, and install @speechify/n8n-nodes-speechify.

Operations

Speech

• Generate Audio — converts input text to an audio file using a chosen voice and model, and writes the result to a binary property on the output item (default data) so it can be passed straight into nodes like Write Binary File, HTTP Request (as a multipart field), or a webhook response. Model, Voice and Language are live dropdowns and they cascade: the selected model narrows the voices and languages to the set it supports (e.g. an English-only model hides non-English voices). Extra options — audio/output format, loudness and text normalization — live under Add Field.

Voice

• Get Many — lists the voices available to your Speechify account, with type / locale filters, "Return All" / "Limit", and a "Simplify" toggle for a trimmed-down voiceId / displayName / gender / locale / languages shape instead of the raw API response. Handy for building your own voice-selection logic; the Generate Audio operation has its own searchable Voice picker, so you don't need this just to find an ID.

Credentials

This node uses the Speechify API credential type: a single API Key field. Generate a key from the Speechify API console and paste it in — the node sends it as Authorization: Bearer <your key> on every request. Use the "Test" button on the credential to confirm it before you build a workflow.

Connect the credential first. The Voice, Model and Language fields are dropdowns populated live from the Speechify API using your key. They only load once a valid credential is selected on the node — until then they stay empty. If a dropdown won't populate, re-check the credential with its "Test" button.

Compatibility

Built and tested against n8n-workflow as scaffolded by @n8n/node-cli (n8n n8nNodesApiVersion: 1). No known incompatibilities.

Usage

All configuration — the API key, the text, the voice, the model, the audio format — is supplied via node parameters and the credential. This node never reads environment variables or the filesystem for configuration, per n8n's community-node verification requirements.

Every request this node sends to api.speechify.ai includes a Speechify-Caller: n8n attribution header (see nodes/Speechify/GenericFunctions.ts) so Speechify can attribute usage to this integration. If you fork this node, keep that header — it's a required piece of the integration, not incidental.

Resources

• n8n community nodes documentation
• Speechify API documentation

Version history

• 0.0.1 — Initial release: Speech → Generate Audio, Voice → Get Many.

Per-release changes are tracked in the GitHub releases and CHANGELOG.md (generated by release-please).

Development

npm install
npm run build
npm run lint

License

MIT