n8n-nodes-speakeasy

n8n community node for the SpeakEasy Speech-to-Text & Text-to-Speech API.

Operations

Transcribe (Speech-to-Text)

Convert audio to text. Supports file upload or URL input.

• Input: Binary audio file or URL
• Formats: mp3, wav, flac, aac, opus, ogg, m4a, mp4, webm
• Output: JSON, verbose JSON (with segments/timestamps), plain text, SRT, or VTT
• Options: Language hint, speaker diarization, word timestamps, translation to English

Synthesize (Text-to-Speech)

Convert text to audio. Returns a binary audio file.

• Input: Text string (up to 4,096 characters)
• Voices: 40+ voices across English, French, Spanish, Japanese, Chinese, Hindi, Italian, Portuguese
• Output: Binary audio in mp3, wav, flac, aac, ogg, or opus
• Options: Speed control (0.5x-2.0x), model selection

Credentials

1. Sign up at tryspeakeasy.io
2. Create an API key in your dashboard
3. In n8n, add a SpeakEasy API credential with your API key

Installation

In n8n

Go to Settings > Community Nodes > Install and enter:

n8n-nodes-speakeasy

Docker

cd /path/to/n8n
npm install n8n-nodes-speakeasy

Example Workflows

Transcribe an uploaded file

1. Webhook node receives an audio file
2. SpeakEasy node (Transcribe) converts it to text
3. Set node formats the output

Generate speech from text

1. Manual Trigger or upstream node provides text
2. SpeakEasy node (Synthesize) generates audio
3. Write Binary File saves the mp3

Links

• SpeakEasy API Docs
• n8n Community Nodes

License

MIT