Text-to-Speech

Resemble AI

premium

Resemble AI is an enterprise-grade text-to-speech provider offering Speech Synthesis, Voice Cloning through Aweb's unified API. It features partial streaming support with standard-tier latency.

Try Resemble AIOfficial docs

Specifications

CategoryText-to-Speech
Auth Typeapi_key
Latency Tierstandard
Streamingpartial
Pricing Tierpremium
Reliabilitystandard
Qualitypremium
Base URLhttps://app.resemble.ai/api/v2
SDK Package

Capabilities (2)

Speech Synthesistts.synthesize
Score: 82
Voice Cloningtts.clone
Score: 86DEFAULT

Quick start

Use Resemble AI through Alfred's unified API — no provider-specific SDK needed.

cURL

curl -X POST https://api.alfred-ai.app/v1/execute \
  -H "Authorization: Bearer $ALFRED_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "provider": "resembleai",
    "capability": "tts.synthesize",
    "input": { "prompt": "Hello from Resemble AI!" }
  }'

TypeScript

import { Alfred } from '@alfred/core';

const alfred = new Alfred({ apiKey: process.env.ALFRED_API_KEY });

const result = await alfred.execute({
  provider: 'resembleai',
  capability: 'tts.synthesize',
  input: { prompt: 'Hello from Resemble AI!' },
});

console.log(result.output);

Related Text-to-Speech providers

ElevenLabs

premium tier

Deepgram

standard tier

Fish Audio

economy tier

Cartesia

standard tier

Getting started →API reference →All capabilities →All providers →