For AI agents: a documentation index is available at the root level at /llms.txt and /llms-full.txt. Append /llms.txt to any URL for a page-level index, or .md for the markdown version of any page.
Status
OverviewProductsManageAPI ReferenceTutorialsClient Libraries
OverviewProductsManageAPI ReferenceTutorialsClient Libraries
    • Overview
  • Quickstarts
    • Synthesize Your First Clip
    • Prompted Synthesis
  • Voice Creation
    • Voice Design Guide
  • WebSocket Streaming
    • Getting Started
    • Receiving Audio Data
    • Python Example
    • Error Handling
  • Prompt Engineering
    • Voice Design Prompting
    • SSML Prompts
Status
LogoLogo
On this page
  • Prerequisites
  • Quick Examples
  • HTTP (curl)
  • Node.js
  • Python
  • Response
  • Next Steps
Quickstarts

Synthesize Your First Clip

Was this page helpful?
Previous

Getting Started

Next
Built with

Learn how to synthesize audio clips using the Resemble API.

Prerequisites

  • Resemble account with confirmed email
  • API key (see Authentication)
  • A voice UUID (use a marketplace voice or create your own)

Quick Examples

HTTP (curl)

$curl --request POST "https://f.cluster.resemble.ai/synthesize" \
>  -H "Authorization: YOUR_API_KEY" \
>  -H "Content-Type: application/json" \
>  --data '{
>    "voice_uuid": "YOUR_VOICE_UUID",
>    "data": "Hello from Resemble!",
>    "sample_rate": 22050,
>    "output_format": "wav"
>  }' \
>  | jq -r '.audio_content' | base64 --decode > output.wav

Node.js

$npm install @resemble/node
1import { Resemble } from "@resemble/node";
2
3Resemble.setApiKey(process.env.RESEMBLE_API_KEY);
4
5const response = await Resemble.v2.clips.createSync("YOUR_PROJECT_UUID", {
6  voice_uuid: "YOUR_VOICE_UUID",
7  body: "Hello from Resemble!",
8  title: "My First Clip"
9});
10
11console.log(response.item.audio_src);

Python

$pip install resemble
1from resemble import Resemble
2import os
3
4Resemble.api_key(os.environ.get("RESEMBLE_API_KEY"))
5
6response = Resemble.v2.clips.create_sync(
7    "YOUR_PROJECT_UUID",
8    "YOUR_VOICE_UUID",
9    "Hello from Resemble!",
10    title="My First Clip"
11)
12
13print(response["item"]["audio_src"])

Response

The synthesis server returns:

1{
2  "success": true,
3  "audio_content": "<base64-encoded-audio>",
4  "audio_timestamps": {
5    "graph_chars": ["H", "e", "l", "l", "o", " ", "f", "r", "o", "m", " ", "R", "e", "s", "e", "m", "b", "l", "e", "!"],
6    "graph_times": [[0.08, 0.12], [0.12, 0.18], [0.18, 0.24], [0.24, 0.30], [0.30, 0.36], [0.36, 0.40], [0.40, 0.46], [0.46, 0.52], [0.52, 0.58], [0.58, 0.64], [0.64, 0.68], [0.68, 0.74], [0.74, 0.80], [0.80, 0.86], [0.86, 0.92], [0.92, 0.98], [0.98, 1.04], [1.04, 1.10], [1.10, 1.16], [1.16, 1.68]],
7    "phon_chars": [],
8    "phon_times": []
9  },
10  "duration": 1.68,
11  "issues": [],
12  "output_format": "wav",
13  "sample_rate": 22050,
14  "seed": 3389672177,
15  "synth_duration": 1.68,
16  "title": null
17}

Decode audio_content from base64 to get the raw audio bytes.

Next Steps

  • Learn about streaming synthesis for lower latency
  • Explore voice cloning to create custom voices
  • See SSML Reference for advanced speech control