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

Audiobook API

Audiobook API: narrate a full manuscript with a voice for each character

Upload a manuscript, give each character a voice, and export the finished audiobook as one file.

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/audiobook/projects
# 1. Create a project from a manuscript
printf '{"name": "The Lighthouse Keeper", "file_base64": "%s", "filename": "manuscript.txt"}' \
  "$(base64 < manuscript.txt | tr -d '\n')" > body.json
curl -X POST "http://127.0.0.1:8100/api/v1/audiobook/projects" \
  -H "Content-Type: application/json" \
  -d @body.json
 
# 2. Generate every segment, then export one file
curl -X POST "http://127.0.0.1:8100/api/v1/audiobook/projects/PROJECT_ID/generate" \
  -H "Content-Type: application/json" -d '{}'
curl -X POST "http://127.0.0.1:8100/api/v1/audiobook/projects/PROJECT_ID/export" \
  -H "Content-Type: application/json" -d '{ "format": "mp3" }'

What developers build with it

The API identifies the speakers in the text and assigns each one a voice. A pronunciation lexicon keeps names and terms consistent across every chapter.

  • Audio editions for a publisher's back list
  • Narrated versions of long reports and documentation
  • Audio dramas with a designed voice for every character
See the product page

Producing audiobooks at scale and want a cloud API?

Join the cloud API waitlist

Endpoints

Audiobook endpoints

MethodPathWhat it does
POST/api/v1/audiobook/projectsCreate a project from a manuscript
POST/api/v1/audiobook/projects/{project_id}/assign-speakersDetect who speaks each line
POST/api/v1/audiobook/projects/{project_id}/design-castDesign a voice for every uncast character
POST/api/v1/audiobook/projects/{project_id}/generateGenerate audio for all segments
POST/api/v1/audiobook/projects/{project_id}/exportExport the finished audiobook

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

Yes. It identifies the speakers in the text, using the LLM you set in the app, and assigns each one a voice. /design-cast can also design a new voice for every character that doesn't have one yet.

Add it to the project's lexicon with POST /api/v1/audiobook/projects/{project_id}/lexicon. The respelling is used on every generation, while the text keeps its normal spelling.

Yes. POST /api/v1/audiobook/projects/{project_id}/segments/{segment_id}/generate regenerates a single segment, and earlier takes stay in its history.

MP3 by default. Send a different format in the body of POST /api/v1/audiobook/projects/{project_id}/export to change it.

Explore

Related APIs

Text to speech

Turn text into speech with preset speakers in 10 languages.

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.