Voice Clone + TTS

Scope

This skill is narrowly scoped to: (1) uploading clone audio to MiniMax, (2) creating a cloned voice, (3) TTS with cloned or existing voices, and (4) updating the cloned-voice mapping block in this SKILL.md. The script only reads/writes this skill’s SKILL.md; it does not read unrelated system files or other environment variables beyond the MiniMax API key(s) above.

When to Use

• Use this skill when you need to clone user-provided audio into a reusable voice.
• Use this skill when you need text-to-speech (TTS) with an already cloned voice.
• For long-term maintenance, cloned results are written back to this file to reduce repeated setup.

API Reference (MiniMax)

• Upload clone audio: POST /v1/files/upload, purpose=voice_clone, multipart/form-data.
• Create cloned voice: POST /v1/voice_clone.
• Speech synthesis: POST /v1/t2a_v2.
• Audio requirements: mp3/m4a/wav, duration 10 seconds–5 minutes, file size <=20MB.