Introducing Song Creator Pro — create music with AI, locally on your device. Try it now →
Voice Creator Pro logoVoice Creator Pro
Try For Free

Text to Speech API

Text to speech API with natural voices and style control

Send text and a speaker name in one request and get a WAV file back.

Available now as a local API in the desktop app. Cloud API coming soon.

Join the cloud API waitlistGet the desktop app
POST/api/v1/tts/generate
curl -X POST "http://127.0.0.1:8100/api/v1/tts/generate?sync=true" \
  -H "Content-Type: application/json" \
  -d '{
    "text": "Welcome to the product tour.",
    "speaker": "Vivian",
    "language": "English"
  }'

What developers build with it

Each request returns up to about 3 minutes of speech. For longer scripts, send one request per paragraph.

  • Narration for product tours, explainers and course lessons, generated from your CMS
  • Spoken versions of articles or newsletters, rebuilt whenever the text changes
  • Voice lines for games and prototypes, regenerated with a fixed seed so takes stay the same
See the product page
Response
{
  "success": true,
  "status": "Generated successfully",
  "audio_base64": "UklGRiQAAABXQVZFZm10..."
}

Want text to speech without running the app locally?

Join the cloud API waitlist

Endpoints

Text to speech endpoints

MethodPathWhat it does
POST/api/v1/tts/generateGenerate speech from text with a preset speaker
GET/api/v1/tts/speakersList the built-in speakers
GET/api/v1/tts/languagesList supported languages
GET/api/v1/generation/progressPoll a generation started without sync

Quickstart

Make your first request in three steps

Install the app, turn on the API and send your first request.

API reference

Full API reference

Every endpoint, with its parameters and responses.

Cloud API

Join the cloud API waitlist

We're building a cloud API. Pick the features you need and roughly how much you'd use, and your answers decide which ones come first.

Which features do you need?

We'll only email you about the API. Unsubscribe anytime.

FAQ

Common Questions

Up to about 3 minutes of speech per request. For longer scripts, send one request per paragraph, or use the audiobook endpoints, which split a manuscript into segments for you.

The preset speakers cover 10 languages. For other languages, clone or design a voice instead: voice cloning and voice design support 600+ languages.

Yes. Pass an instruct string with the request, for example "speak slowly and warmly", and the speaker reads the text in that style. A seed in generation_params keeps results repeatable.

No. The local API is part of the desktop app, a one-time purchase, so there is no per-character or per-request fee. Generation runs on your own computer.

Explore

Related APIs

Voice cloning

Clone a voice from a short clip and speak new text with it.

Voice design

Describe a voice in words and generate speech in it.

Speech to text

Transcribe audio with word timestamps and speaker labels.

Dubbing

Dub videos into 21 languages, keeping each speaker's voice.

Subtitles

Generate SRT caption files with word-level timing.

Clips

Cut long videos into short, captioned clips.

AI Cut

Remove silences, filler words and bad takes, then render.

Avatars

Make a lip-synced talking-head video from one photo.

Voice changer

Re-voice a recording while keeping its timing and emotion.

Audiobooks

Narrate a manuscript with a voice for every character.