# CastReader Voice API > A REST text-to-speech API for multilingual audio with private, authorized cloned voices. ## Build with an AI coding tool - [Integration guide](https://voice.castreader.com/integrations/ai-coding): evaluate fit, access, audio evidence, recovery and total cost. - [Complete developer context](https://voice.castreader.com/llms-full.txt): installation, contracts, errors and application acceptance tests. - [Connection check script](https://voice.castreader.com/examples/connection-check.mjs): server-side Node.js checks for key, region, language, a ready voice and estimated balance. No generation request or generation charge. Passing is not an audio-quality or live-capacity guarantee. - [Capabilities and pricing JSON](https://voice.castreader.com/integration-manifest.json): public configuration, not worker health or a quality guarantee. - [First-party test report](https://voice.castreader.com/reports/api-verification): planned 3 voices × 10 languages; 29 additional saved outputs, 1 terminal failures retained, 0 pending recovery, 0 not submitted, plus the earlier 23-case baseline. Downloadable audio, charges and machine transcripts; native-speaker review remains pending; [JSON report](https://voice.castreader.com/reports/api-verification.json). ## Current product facts - Canonical website: https://voice.castreader.com - Product owner: CastReader, https://castreader.com - Access: verified CastReader accounts can activate the existing trial immediately, without manual approval; one trial grant per account. - Language: en, zh, de, ja, fr, es, ko, pt, ru, it. - Model alias: clone-v1. - Formats: complete MP3 and WAV audio files. - Homepage demo: no login or API key required; editable text, default voices, up to 500 characters and 3 successful trials per visitor per day, subject to IP and platform caps. Uses platform allowance, never a personal wallet. - Complete job audio: GET /v1/jobs/{job_id}/audio returns all segments merged, with aggregate usage headers; downloads do not incur another generation charge. - Optional speech timestamps: return_timestamps=true uses qwen-pcm-measured-groups-v3 for English word or measured word-group alignment. Read GET /v1/requests/{request_id}/timestamps. No extra fee; optional alignment may be unavailable while successful audio is charged once. - Queued speech: enabled, POST /v1/jobs; maximum 500 normalized characters; 600 second task deadline. - Concurrency: 1 generation per workspace. Availability is shared and variable. - Price: USD 8 per million billable Unicode code points after NFC normalization. Internal spaces and punctuation count. This is not UTF-8 byte billing. - Trial: 3000 characters after activation, valid for 30 days; daily allowance applies. - No monthly API subscription. API wallet and voices are separate from CastReader reading apps and Pro. - Successful retained result: downloadable for up to 24 hours without another generation charge. - Not currently offered: real-time speech, streaming, long-form requests, a latency/uptime SLA or an EU-region deployment. - 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. ## Primary sources - [API overview](https://voice.castreader.com/): Product workflow, fit and current limits. - [Voice library](https://voice.castreader.com/voices): Complete selectable shared catalog, free anonymous previews, language/gender/style filters and pagination. Private clones stay private. [Live catalog JSON](https://voice.castreader.com/voices/catalog.json) contains catalog IDs and use URLs, not generation voice IDs. - [Multilingual voice cloning API](https://voice.castreader.com/voice-cloning-api): Authorized recording, reusable voice IDs and synthesis-language boundaries. - [Pricing](https://voice.castreader.com/pricing): Character metering, trial, prepaid balance and calculation examples. - [Developer documentation](https://voice.castreader.com/docs): Authentication, voices, queued tasks, retries and usage. - [Speech timestamps](https://voice.castreader.com/docs/timestamps): v3 alignment, response examples, retention and billing. - [Multilingual flashcard project](https://voice.castreader.com/guides/multilingual-flashcard-audio): 20 real audio files, runnable Node.js example, safe resume and actual usage; an application loop, not a native batch endpoint or customer case. - [Capabilities](https://voice.castreader.com/docs/overview/capabilities): Current enabled capabilities. - [OpenAPI 3.1](https://voice.castreader.com/openapi.json): Machine-readable request and response contract. - [Data and voice permissions](https://voice.castreader.com/data): Processing regions and voice authorization. - [Get started](https://voice.castreader.com/request-access): Verified-account trial activation, no manual approval. ## Product questions ### What is the CastReader Voice API? 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. ### 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 $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. ### 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 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. ### 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. - [CastReader for Codex](https://voice.castreader.com/integrations/codex): install the Git marketplace package, build runnable speech features or generate audio with charge receipts. Version 0.1 uses local skills and an API key; OpenAI directory approval is separate. ## Selection and listening evidence - [Compare TTS APIs](https://voice.castreader.com/compare/tts-apis): six providers, dated official sources, billing units and limits; [JSON](https://voice.castreader.com/compare/tts-apis.json). Not an independent audio comparison or lowest-price guarantee. Free-model caveats remain visible; output audio tokens are not inferred from characters. - [Cross-language listening review](https://voice.castreader.com/reports/listening-review): review real stored samples and export local pronunciation, naturalness and similarity scores. The tool is not evidence that native-speaker review has been completed.