CastReader for developers

Text to speech API.
Your voice,
in your product.

Turn short English text into audio with a private voice you have permission to use. One REST API, reusable voice IDs, and a clear cost for every successful request.

Request API access Read the quickstart

Developer preview · Access by invitation · 3,000 trial characters after activation.

Explore your first requestWhat would your product say?

46 / 120 characters$0.000552 at the paid rate

cURL · POST /v1/jobs

curl https://voice.castreader.com/v1/jobs \
  -H "Authorization: Bearer $CASTREADER_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $REQUEST_KEY" \
  --fail-with-body --data-binary @- <<'JSON'
{
  "model": "clone-v1",
  "voice_id": "YOUR_VOICE_ID",
  "text": "Give your product a voice that feels like you.",
  "language": "en",
  "output_format": "mp3"
}
JSON

202 Accepted → save job ID → check status → download audio

This example updates locally; it does not generate audio or spend credits. Set your key, voice ID and a saved request key before running it. Complete quickstart →

$12 / 1M charactersNo monthly API subscription

Private voicesReusable, workspace-owned voice IDs

MP3 + WAVAudio files you can save and use

Queued REST APIcURL, Node.js and Python guides

A familiar voice. A clear contract.

Speech your application can work with.

Keep the voice consistent, understand the bill, and pick up where a request left off.

A voice that stays yours

Create a private voice from a recording you are authorized to use. Reuse its ID across prompts instead of uploading a reference for every request.

Voice cloning workflow →

Know the cost before the call

Count normalized characters, estimate the cost, and check actual usage in the console. Playground and your backend follow the same billing rules.

Pricing and character calculator →

Retries that respect your balance

A stable task ID and idempotency key let you check progress and recover saved audio. The same successful request is charged once.

Retries, errors and recovery →

From recording to request

One voice. Three ways to add it.

Record yourself, invite a speaker to record, or upload an existing audio file. Each path creates a private voice in your API workspace.

Get access and a key

Activate developer access, sign in with your CastReader account, and create a named API key.

Add an authorized voice

Use a clean, single-speaker reference. Keep the voice ID once processing completes.

Submit, check, download

Send your text, save the task ID, and download the finished audio. Inspect the usage record in your console.

Prepare a recording →Follow a queued request →Voice permissions →

Start with a small, useful interaction

Built for speech that can wait a moment.

The current preview fits short audio generated ahead of playback. Start with one workflow and a voice your users recognize.

LEARNING

Flashcards with a familiar voice

Generate short example sentences and learning prompts, then save the audio alongside each card.

“A little practice, every day.”

PRODUCT EXPERIENCES

A personal welcome

Create brief welcome messages or guided instructions in a consistent, authorized product voice.

“Welcome back. Let’s get started.”

CONTENT TOOLS

Short clips, ready to reuse

Add a voice step to a content workflow and retrieve the finished file when the queued task completes.

“Your next chapter starts here.”

Pay as you go

Small requests.
Understandable costs.

No monthly API subscription. Use your available trial first, then top up a separate API wallet.

Explore API pricing

$12 / million characters

100 paid characters: $0.0012
10,000 paid characters, across requests: $0.12
Waiting in the queue: Free
Download the same retained result: No new charge

Billable characters are Unicode code points after NFC normalization. Internal spaces and punctuation count. Trial allowances and current limits apply.

Available in this preview

Know the fit before you integrate.

We publish the current limits alongside the API contract. Check these before planning a production workflow.

Full capabilities and limits →

Language: English
Text per task: Up to 120 characters
Generation: 1 at a time; queue supported
Task deadline: 10 minutes; waiting is free
Output: MP3 or WAV file
Real-time / streaming: Not available in this preview
Processing region: One website, account, API key and prepaid wallet. Account, billing and resource metadata use the US control plane. The dispatch API selects China for mainland-China networks and the US elsewhere. Text, reference recordings, inference and private audio stay in the selected region, with no cross-region voice-data fallback.

Developer resources

The details, ready to build with.

INTEGRATE

REST quickstart ↗

Submit a task, poll for completion and retrieve the audio.

REFERENCE

OpenAPI 3.1 ↗

Explore the machine-readable request and response contract.

PRODUCT FACTS

Capabilities & limits ↗

Formats, language, pricing units and what is currently enabled.

Straight answers

Before your first API call.

What is the CastReader Voice API?

CastReader Voice API is a REST text-to-speech service for generating English audio with private, authorized cloned voices. It returns MP3 or WAV and provides API keys, queued tasks, usage records, and a separate prepaid wallet.

How is the API different from the CastReader reading apps?

The browser extension and mobile apps help people listen to content. Voice API lets developers generate audio inside their own products. You use your CastReader identity, but API access, credits, voices, and usage are managed separately. A Pro reading plan does not include API usage.

How much does text to speech cost?

Successful generation costs $12 per million billable characters, with no monthly API subscription. A paid 100-character request costs $0.0012. Available trial characters are used first. Characters are Unicode code points after NFC normalization, including internal spaces and punctuation; this is not UTF-8 byte billing.

Can I use my own voice or a voice someone shares with me?

You can create a private voice from an authorized recording. The console offers self-recording, a recording invitation, and audio upload. You need the speaker’s permission for cloning and your intended use. Personal voices from the reading apps are not automatically imported into API workspaces.

Is this a real-time or long-form speech API?

The current preview is for short English speech and queued workflows. It does not offer real-time conversations, streaming, or an uptime or latency SLA. Check the published capabilities for current input limits before integrating.

What happens if I retry or close the browser?

A queued task persists when you leave the page. Save its job ID and the original Idempotency-Key. Repeating the same input with that key returns the same task; downloading a retained successful result does not generate or charge again. Waiting and tasks cancelled before execution are free.

Where is API data processed?

One website, account, API key and prepaid wallet. Account, billing and resource metadata use the US control plane. The dispatch API selects China for mainland-China networks and the US elsewhere. Text, reference recordings, inference and private audio stay in the selected region, with no cross-region voice-data fallback. International voice data is separate from the China service, with no automatic cross-region fallback. See the data and voice permissions page for handling and retention rules.

Bring your own voice

Build something worth listening to.

Tell us what you are building, or explore the API before you commit.

Request API access ↗Explore the documentation →

Already have access? Open your console.

Text to speech API.Your voice,in your product.