彦国 孙 v1.0.4
AI voice generator from text
Save this plugin to Following and return to review observed changes. Follow up to 10 plugins free.
From the marketplace listing
TTSStudio is an AI text-to-speech generator and AI voice generator that converts user-provided written text into natural-sounding MP3 speech. It gives ChatGPT users an interactive workspace for turning scripts, articles, documents, lessons, stories, notes, and other written content into clear spoken audio without recording a voice manually. Use TTSStudio to create narration, AI voiceovers, read-aloud audio, podcast segments, audiobook passages, e-learning lessons, training materials, presentation audio, social media voice tracks, advertising voiceovers, and accessible audio versions of written content. When a user asks ChatGPT to turn text into speech, TTSStudio opens the workspace with the supplied text prefilled. The user can review the source text, choose how it should sound, and start generation only when ready. The voice catalog can be browsed and filtered to find an appropriate AI voice for the language, style, audience, and use case. Users can preview voices, compare available options, and refine the delivery by adjusting emotion, speed, pitch, and volume before generating the final audio. Each generation uses the applicable TTSStudio allowance and saves the result to the user's private audio history. The workspace can display recent completed or failed generations, replay completed speech, manage saved history items, delete a selected result, and show the download actions available for the user's plan. This makes it easier to return to previous voiceovers, review alternative versions, and keep generated audio organized. TTSStudio focuses specifically on text-to-speech generation from text supplied by the user. By keeping text review, AI voice selection, speech customization, generation, playback, history, and downloads in one workflow, TTSStudio helps users convert written ideas into reusable spoken audio directly from ChatGPT.
Language: English · Automatically detected from descriptions.
Oct 27, 2026 · 1 saved observations
Metadata · Oct 27, 2026 · 00:45 UTC · Compared with Oct 24, 2026 · 13:31 UTC
Package or technical metadata updated
Observed in package metadata. These changes alone do not establish a new customer-facing feature.
Oct 24, 2026 · 13:31 UTC
Not present
Oct 27, 2026 · 00:45 UTC
false
From the developer’s listing and package; capabilities are not independently tested. Package observed Nov 3, 2026.
Review scenarios; not an exhaustive list.
Pricing and account requirements have not been established from the available package declarations. Unknown pricing does not mean free access.
Turn the following text into natural-sounding speech
--- name: ttsstudio-faq description: Answer TTSStudio product questions about text-to-speech, voice selection, delivery settings, allowance, audio history, downloads, account connection and workspace problems. Use for TTSStudio help in the user's language. --- # TTSStudio FAQ Answer in the user's language. Give a direct answer and the next useful step. Read [the product FAQ](references/faq.md) for the relevant behavior and limits. General help does not require opening the workspace or connecting an account. ## When tools help | User intent | Response or action | | --- | --- | | Explain voices, settings, limits, downloads or account connection | Answer from the FAQ. Do not call a tool just to explain the product. | | Open the workspace, create speech, choose a voice or preview delivery | Use `open-tts-studio` when exposed by the host. Prefill only text supplied or explicitly approved by the user. Opening the workspace does not start generation. | | Review, replay or manage existing audio | Open the workspace when requested and guide the user to its history controls. Read exact results from the connected workspace. | | Transcribe audio, clone a voice, generate music or manage a subscription | Explain the relevant limitation. Do not claim TTSStudio completed an unsupported action. | The user reviews the text and starts generation inside the workspace. Follow the tools actually exposed by the host. In the current server, `generate-speech`, `list-speech-history` and `delete-speech-history-item` are app-only tools used by the widget; do not invoke them from the conversation or invent their arguments, history references or results. ## Keep answers grounded - Do not invent source text, generate speech from a general help request, or imply that opening the workspace consumes allowance. - Do not claim a ChatGPT attachment has been imported. Ask the user to provide the text they want spoken or paste it into the workspace. - Voice availability, account allowance, generation status and download access must come from the current workspace. Do not infer them from this FAQ. - If a generation's outcome is uncertain, check existing history before recommending another submission; repeated clicks can consume allowance again. - Deleting audio is permanent. The user selects the item and confirms deletion inside the widget. Do not turn account-deletion requests into audio deletion. - Explain errors accurately. A connected workspace or successful tool opening does not prove audio was generated, played or downloaded. - Use the published support, privacy, terms and pricing pages for questions governed by those pages. Do not invent refunds, discounts, free allowances, usage rights or retention commitments. - For unrelated requests, answer normally without invoking this plugin.
Referenced files: 1 — file references are metadata, not package contents.
Updated subtitles and complete product descriptions in 63 languages.
Declared in the saved package. Remote tools may change independently.
Publisher declarations from the archived package. These are separate from our research and the live service's terms.
Package observed Nov 3, 2026.
plugin_asdk_app_6a9137aa685481919044f3a35c44f8bd
Download plugin data (JSON)