Current availability
- Web studio
- Use the studio to sign in and generate speech.
- ChatGPT
- Check installation status. Publisher identity verification for the OpenAI plugin directory is not yet complete. A private test connection does not imply a public listing.
- Codex
- Read the plugin connection guide. Installation availability reflects verified release status.
First-release voices and languages
The first public release uses Qwen Audio 3.0 TTS Plus (Beijing) for ordinary narration in Mandarin Chinese and English, with two bilingual voices: female longanlingxin and male longanlufeng. Style and emotion prompts are not available in this release.
The archival Cherry recording on the examples page uses an older engine and does not demonstrate these voices. Actual input and queue limits are shown by the studio.
The web studio workflow
- Write or upload your scripts
Use single-script mode for a complete narration or batch mode for scripts separated by blank lines. UTF-8 text and JSONL input are supported.
- Choose the sound
Select an available female or male voice, Mandarin Chinese or English, speed, and output format. Style prompts are not available in the first public release.
- Generate, listen, and save
Check task progress, listen to clips, and download WAV, MP3, or a ZIP. After a refresh, the studio attempts to recover the most recent task.
Settings and output
- Voices and languages
- The first public release has two bilingual voices for Mandarin Chinese and English. Website translation does not imply additional speech languages.
- Speed
- The studio shows the available speed range. Listen to check names, numbers, and pauses.
- Style and emotion
- The first public release does not accept style or emotion prompts. Nonempty style text must be removed before generation.
- WAV and MP3
- WAV is useful for further audio processing. MP3 is convenient for listening and distribution.
- Batch ZIP
- Clips and a manifest follow the original submission order. Large results can be viewed in pages.
- Errors and recovery
- Fix invalid input before resubmitting. Try later when the queue is full. Resolve provider or network errors before resuming the original task.
Scripts and results
The server sends the script to its configured speech provider. Production retention periods and deletion rules are described in the privacy notes. User scripts, task links, generated audio, and accounts are excluded from the public sitemap.
Connect through ChatGPT
Check ChatGPT installation, authorization, and prompt examples.
Connect through Codex
Other MCP clients
Claude, Cursor, and other clients have not completed end-to-end verification. Protocol support alone does not establish that authorization, interface behavior, and downloads work in a particular client.