Create AI Voice Responses for Slack Bots

Slack Event  →  Slack Bot (Python/Node)  →  ElevenLabs TTS  →  Audio File  →  Slack Message with Attachment

# app.py
import os
import json
import requests
from flask import Flask, request, jsonify

app = Flask(__name__)

SLACK_BOT_TOKEN = os.getenv("SLACK_BOT_TOKEN")
ELEVENLABS_API_KEY = os.getenv("ELEVENLABS_API_KEY")
ELEVENLABS_URL = "https://api.elevenlabs.io/v1/text-to-speech/eleven_monolingual_v1"

# 1️⃣ Helper: Post file to Slack
def upload_to_slack(file_bytes, filename, channels):
    url = "https://slack.com/api/files.upload"
    headers = {"Authorization": f"Bearer {SLACK_BOT_TOKEN}"}
    files = {"file": (filename, file_bytes, "audio/mpeg")}
    data = {"channels": channels, "title": filename}
    resp = requests.post(url, headers=headers, files=files, data=data)
    return resp.json()

# 2️⃣ Helper: Generate TTS via ElevenLabs
def generate_tts(text, voice_id="EXAVITQu4vr4xnSDxMaL"):
    headers = {
        "xi-api-key": ELEVENLABS_API_KEY,
        "Content-Type": "application/json",
    }
    payload = {
        "text": text,
        "voice_settings": {
            "stability": 0.5,
            "similarity_boost": 0.75,
        },
    }
    resp = requests.post(ELEVENLABS_URL, headers=headers, json=payload)
    resp.raise_for_status()
    return resp.content  # binary MP3

@app.route("/slack/events", methods=["POST"])
def slack_events():
    data = request.get_json()
    # URL verification challenge
    if data.get("type") == "url_verification":
        return jsonify({"challenge": data["challenge"]})

    # Handle event callbacks
    event = data.get("event", {})
    if event.get("type") == "app_mention":
        user = event.get("user")
        channel = event.get("channel")
        text = event.get("text").replace("<@{}>".format(event.get("bot_id", "")), "").strip()
        # 3️⃣ Generate audio
        audio = generate_tts(text)
        # 4️⃣ Upload to Slack
        upload_to_slack(audio, "bot_response.mp3", channel)
        return "", 200

    return "", 404

if __name__ == "__main__":
    app.run(port=3000)

// server.js
require('dotenv').config();
const express = require('express');
const fetch = require('node-fetch');
const { IncomingForm } = require('formidable');

const app = express();
const SLACK_BOT_TOKEN = process.env.SLACK_BOT_TOKEN;
const ELEVENLABS_API_KEY = process.env.ELEVENLABS_API_KEY;
const ELEVENLABS_URL = 'https://api.elevenlabs.io/v1/text-to-speech/eleven_monolingual_v1';

app.use(express.json());

async function generateTTS(text) {
  const res = await fetch(ELEVENLABS_URL, {
    method: 'POST',
    headers: {
      'xi-api-key': ELEVENLABS_API_KEY,
      'Content-Type': 'application/json',
    },
    body: JSON.stringify({
      text,
      voice_settings: { stability: 0.5, similarity_boost: 0.75 },
    }),
  });
  return res.buffer(); // binary
}

async function uploadToSlack(fileBuffer, channels) {
  const form = new IncomingForm();
  form.append('channels', channels);
  form.append('title', 'bot_response.mp3');
  form.append('file', fileBuffer, { filename: 'bot_response.mp3' });

  const res = await fetch('https://slack.com/api/files.upload', {
    method: 'POST',
    headers: { Authorization: `Bearer ${SLACK_BOT_TOKEN}` },
    body: form,
  });
  return res.json();
}

app.post('/slack/events', async (req, res) => {
  const { type, challenge, event } = req.body;
  if (type === 'url_verification') return res.send({ challenge });

  if (event && event.type === 'app_mention') {
    const text = event.text.replace(/<@.*?>/, '').trim();
    const audio = await generateTTS(text);
    await uploadToSlack(audio, event.channel);
    return res.sendStatus(200);
  }
  res.sendStatus(404);
});

app.listen(3000, () => console.log('Listening on 3000'));

# Example of cloning a voice
voice_id = "my_custom_voice"  # from ElevenLabs
audio = generate_tts("Hello, I’m your new bot!", voice_id=voice_id)