Generate speech audio from text using the z-ai-web-dev-sdk TTS API.
npx skills add https://github.com/tmtgroupbot/lptracker-deploy --skill tts-tmtgroupbot
Please help me install this Agent Skill. Skill: TTS Source: https://github.com/tmtgroupbot/lptracker-deploy/tree/main/skills/TTS Command: npx skills add https://github.com/tmtgroupbot/lptracker-deploy --skill tts-tmtgroupbot
High-intent search queries and answers about installing and using this skill.
Import z-ai-web-dev-sdk, create an instance with ZAI.create(), then call zai.audio.tts.create() with your input text, voice, speed, and response_format. Convert the returned Response via response.arrayBuffer() and write it to a file with fs.writeFileSync.
The API supports WAV, MP3, and PCM output formats for non-streaming requests. When streaming is enabled with stream: true, only the PCM format is supported, and audio is generated at a 24000 Hz sample rate.
No, z-ai-web-dev-sdk must be used in backend code only, never in client-side code. For web apps, expose it through a server endpoint such as a Next.js API route or Express.js handler that returns the audio buffer.
The API limits input to 1024 characters per request, so longer text causes errors. Split the text into sentence-based chunks under the limit, generate audio for each chunk, and combine the resulting files.
The SDK returns a standard Response object without an audio property. Call await response.arrayBuffer() on the response, then convert it with Buffer.from(new Uint8Array(arrayBuffer)) before saving.
cas-bigdatalabClean English research text by expanding abbreviations and correcting spelling.
Andrew-GirgisCreate interactive web UIs for machine learning models with Gradio.
lvhuanidTranscribe spoken audio into written text using the z-ai-web-dev-sdk.
missingbulbWire browser speech recognition and text-to-speech APIs into web applications.
