Get startedQuickstart

Voice Cloning Quickstart

Clone a voice and synthesize with it in minutes

The fastest path to a working cloned voice: a short sample, a consent record, one create call, and you are synthesizing in the new voice.

Cloning requires the speaker’s consent. You will pass a consent record with a full name and email on the create call.
1

Set your API key

$export SPEECHIFY_API_KEY="your-api-key-here"
2

Record a sample

Capture 10-30 seconds of clean speech, under a minute and under 5MB. Avoid background noise.

3

Create the voice

POST
/v1/voices
1curl -X POST https://api.speechify.ai/v1/voices \
2     -H "Authorization: Bearer <token>" \
3     -H "Content-Type: multipart/form-data" \
4     -F avatar=@<file1> \
5     -F consent="string" \
6     -F gender="male" \
7     -F name="string" \
8     -F sample=@string
Try it

Keep the voice_id from the response.

4

Synthesize

Pass the voice_id to the speech endpoint:

POST
/v1/audio/speech
1curl -X POST https://api.speechify.ai/v1/audio/speech \
2     -H "Authorization: Bearer <token>" \
3     -H "Content-Type: application/json" \
4     -d '{
5  "input": "Hello! This is the Speechify text-to-speech API.",
6  "voice_id": "geffen_32",
7  "audio_format": "mp3",
8  "model": "simba-3.2"
9}'
Try it
Response
1{
2  "audio_data": "example",
3  "audio_format": "wav",
4  "billable_characters_count": 10,
5  "speech_marks": {
6    "chunks": [
7      {}
8    ],
9    "end": 1,
10    "end_time": 1,
11    "start": 1,
12    "start_time": 1,
13    "type": "example",
14    "value": "example"
15  }
16}
Use simba-english or simba-multilingual for cloned voices. The curated simba-3.2 set does not play cloned voices.

Next steps

Voice Cloning API

Required fields, model support, and voice management.

Overview

Concepts and quality tiers for voice cloning.