generate_tts
Convert text to spoken audio using ElevenLabs. Choose fast or high-quality models, select voice, and download the result.
Instructions
Generate speech from text using ElevenLabs via kie.ai. Supports Turbo 2.5 (fast) and Multilingual V2 (high quality). Downloads to kie/assets/raw/.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| text | Yes | Text to synthesize into speech | |
| wait | No | Set false to submit and return immediately with the task_id (async mode) — then poll with check_task and fetch with download_result. Recommended for long generations to avoid client-side watchdog timeouts. | |
| model | No | turbo-2-5=fast, multilingual-v2=high quality with language support | turbo-2-5 |
| speed | No | Speech speed (0.7–1.2). Only for multilingual-v2. | |
| filename | No | Output filename. Auto-generated if omitted. | |
| voice_id | No | Voice name (e.g. "Bella", "Viking Bjorn", "Aria") or kie voice ID. kie.ai only accepts its curated ~67-voice set — arbitrary ElevenLabs voice IDs are rejected. An unknown value returns the full catalog. Optional — defaults to James. | |
| download_dir | No | Absolute directory to save the file(s) into (created if missing). Defaults to the server's kie/assets/raw/. Must be absolute — the MCP server's working directory is not the caller's. | |
| language_code | No | Language code for multilingual-v2 (e.g. "en", "es", "fr", "ja") | |
| max_wait_seconds | No | Override the blocking-mode polling budget in seconds (defaults: image 600, video 900, audio 300, speech 300). Ignored when wait=false. |