Token Plan Speech

Call Qwen Token Plan speech models on the Personal allowlist (TTS, ASR, realtime). Activate for text-to-speech, speech-to-text, or live voice on Token Plan.

ariffazil Updated

File contents

Speech on Qwen Token Plan only. Capability SOT: CAPABILITIES.json (audio_in / audio_out).

User request: $ARGUMENTS

Allowlist (exact IDs)

Model Job
qwen-audio-3.0-tts-plus Default TTS + clone/instruct
qwen-audio-3.0-asr-flash Speech-to-text
qwen-audio-3.0-realtime-plus Realtime conversation

Pay-as-you-go CosyVoice / qwen3-tts-vd-* / Omni S2S are not on Token Plan Personal. Do not call them on this key.

S2S vs pipeline (from docs): S2S for live talk; pipeline (ASR + LLM + TTS) when you need voice design/clone control.

Notes

ariffazil/openclaw-workspace/tree/main/skills/token-plan-speech commit d40ad38475

Frequently asked questions

npx skillmds@latest add ariffazil/token-plan-speech