CastReader Voice APICastReader for developers
Give your product a voice people remember. Start with a ready-to-use voice or clone one you have permission to use, then bring it to your app with a simple API.
$8/ 1M charactersAffordable multilingual voice cloningPay as you go · No monthly API subscriptionDeveloper preview · 3,000 trial characters after activation.
Checking supported languages…
No sign-up needed
3 free generations per day
Edit the text and make it yours. Homepage trials never charge your wallet.
VOICE API · CAPABILITIES
Three building blocks, ready for your next product.
Browse the complete shared library without signing up. Filter by sample language, gender and style; preview first, then use your choice in your app.
await client.generate({
voice: 'rowan',
text: 'Every story needs a voice.',
language: 'en',
});Clone an authorized recording. Reuse its voice ID to speak text in a supported language.
voiceId// voiceId: your prepared clone
await client.generate({
voice: voiceId,
text: '让每一句话，都有你的声音。',
language: 'zh',
});Get English word or word-group intervals. Build reading highlights and synchronized captions.
{
"text": "Hello from CastReader.",
"language": "en",
"return_timestamps": true
}start_time → end_timeMeasured intervals · secondsFOR AI-ASSISTED DEVELOPMENT
Evaluate fit, hear actual outputs, check the cost and give your coding assistant a concrete integration contract.
// Official context, examples and limits
GET /integration-manifest.json
GET /openapi.json
GET /reports/api-verification.jsonA familiar voice. A clear contract.
Keep the voice consistent, understand the bill, and pick up where a request left off.
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 →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 →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
Record yourself, invite a speaker to record, or upload an existing audio file. Each path creates a private voice in your API workspace.
Activate developer access, sign in with your CastReader account, and create a named API key.
Use a clean, single-speaker reference. Keep the voice ID once processing completes.
Send your text, save the task ID, and download the finished audio. Inspect the usage record in your console.
Pay as you go
No monthly API subscription. Use your available trial first, then top up a separate API wallet.
Explore API pricing$8 / million characters
Billable characters are Unicode code points after NFC normalization. Internal spaces and punctuation count. Trial allowances and current limits apply.
Available in this preview
We publish the current limits alongside the API contract. Check these before planning a production workflow.
Full capabilities and limits →Developer resources
Straight answers
CastReader Voice API is a REST text-to-speech service with a selectable voice library and private, authorized voice cloning. Generate speech in the configured languages for reading, learning, voiceovers and product guidance. It returns MP3 or WAV and provides queued tasks and usage records.
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.
Successful generation costs $8 per million billable characters, with no monthly API subscription. A paid 100-character request costs $0.0008. 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.
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.
The current preview is for short speech and queued workflows. Longer content needs application-side splitting and playback assembly. It does not offer real-time conversations, streaming, or an uptime or latency SLA. Check the published capabilities for current input limits before integrating.
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.
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
Tell us what you are building, or explore the API before you commit.
Already have access? Open your console.
