ressemble

Original source / Raw SKILL.md

---
name: ressemble
displayName: Ressemble - Adriano
version: 1.0.0
description: Text-to-Speech and Speech-to-Text integration using Resemble AI HTTP API.
author: Adriano Vargas
tags: [tts, stt, audio, ai, voice]
---

# Ressemble – Text & Voice AI Integration

This skill integrates OpenClaw with the Resemble AI HTTP API, enabling:

- 🎙 Speech-to-Text (audio transcription)
- 🔊 Text-to-Speech (voice synthesis)

It uses direct HTTP calls to Resemble's production endpoints and supports asynchronous transcription polling.

---

## Features

### resemble-tts
Generate high-quality speech audio from text input.

Supports:
- Custom `voice_uuid`
- MP3 output format
- Base64 audio return

### resemble-stt
Transcribe audio files to text using Resemble AI.

Supports:
- Multipart audio upload
- Automatic polling until transcription is complete
- Returns clean transcript text

---

## Requirements

You must define the environment variable:

```bash
export RESEMBLE_API_KEY="your_api_key_here"


---

## Skill Companion Files

> Additional files collected from the skill directory layout.

### _meta.json

```json
{
  "owner": "adriano-vr",
  "slug": "ressemble",
  "displayName": "Ressemble TTS e STT",
  "latest": {
    "version": "1.0.1",
    "publishedAt": 1771954042125,
    "commit": "https://github.com/openclaw/skills/commit/7190d92f9fd6c2ef3801a356fe019c33a83a4c7a"
  },
  "history": [
    {
      "version": "1.0.0",
      "publishedAt": 1771876037146,
      "commit": "https://github.com/openclaw/skills/commit/bfba510a2a3b791e1de3a7519ae9e23d31cc7a35"
    }
  ]
}

```

### scripts/stt.sh

```bash
#!/usr/bin/env bash
set -euo pipefail

if [[ "${1:-}" == "" ]]; then
  echo "Usage: stt.sh <audio-file>"
  exit 1
fi

INPUT_AUDIO="$1"

if [[ ! -f "$INPUT_AUDIO" ]]; then
  echo "File not found: $INPUT_AUDIO"
  exit 1
fi

if [[ -z "${RESEMBLE_API_KEY:-}" ]]; then
  echo "Missing RESEMBLE_API_KEY"
  exit 1
fi

echo "🎤 Sending audio for transcription..."

RESPONSE=$(curl -s -X POST "https://app.resemble.ai/api/v2/speech-to-text" \
  -H "Authorization: Bearer $RESEMBLE_API_KEY" \
  -F "file=@${INPUT_AUDIO}")

JOB_ID=$(echo "$RESPONSE" | jq -r '.id')

if [[ "$JOB_ID" == "null" ]]; then
  echo "Failed to create STT job"
  echo "$RESPONSE"
  exit 1
fi

STATUS="processing"

while [[ "$STATUS" == "processing" ]]; do
  sleep 2
  STATUS=$(curl -s "https://app.resemble.ai/api/v2/speech-to-text/${JOB_ID}" \
    -H "Authorization: Bearer $RESEMBLE_API_KEY" | jq -r '.status')
done

if [[ "$STATUS" != "completed" ]]; then
  echo "Transcription failed"
  exit 1
fi

TRANSCRIPT=$(curl -s "https://app.resemble.ai/api/v2/speech-to-text/${JOB_ID}" \
  -H "Authorization: Bearer $RESEMBLE_API_KEY" | jq -r '.transcript')

echo "$TRANSCRIPT"

```

### scripts/tts.sh

```bash
#!/usr/bin/env bash
set -euo pipefail

if [[ "${1:-}" == "" ]]; then
  echo "Usage: tts.sh \"text\" [VOICE_UUID]"
  exit 1
fi

TEXT="$1"
VOICE_UUID="${2:-01aa67f7}"
OUTPUT_FILE="/tmp/resemble_$(date +%s).mp3"

if [[ -z "${RESEMBLE_API_KEY:-}" ]]; then
  echo "Missing RESEMBLE_API_KEY"
  exit 1
fi

echo "🔊 Generating speech..."

RESPONSE=$(curl -s -X POST "https://f.cluster.resemble.ai/synthesize" \
  -H "Authorization: Bearer $RESEMBLE_API_KEY" \
  -H "Content-Type: application/json" \
  -d "{
    \"voice_uuid\": \"$VOICE_UUID\",
    \"data\": \"$TEXT\",
    \"output_format\": \"mp3\"
  }")

SUCCESS=$(echo "$RESPONSE" | jq -r '.success')

if [[ "$SUCCESS" != "true" ]]; then
  echo "TTS failed:"
  echo "$RESPONSE"
  exit 1
fi

echo "$RESPONSE" | jq -r '.audio_content' | base64 -d > "$OUTPUT_FILE"

echo "MEDIA:$OUTPUT_FILE"

```