text-to-speechlisted
Install: claude install-skill popnow-ai/popnow-skills
# Text-to-speech voiceovers
PopNow serves several text-to-speech engines behind one key. Gemini 3.8 Flash TTS follows style directions such as "warm and slow"; MiniMax Speech 2.8 HD gives studio-quality narration and Turbo is cheaper; Qwen3 TTS and Seed Speech cover Chinese and English; Grok TTS is another option.
## Models
These are the PopNow model paths at the time of writing. Confirm them with `models` before use; newer versions appear there first.
| Model path | Best for |
|---|---|
| `google/gemini-3.8-flash-tts/text-to-speech` | Directable style, many languages |
| `google/gemini-3.8-flash-lite-tts/text-to-speech` | Cheaper Gemini voice |
| `minimax/speech-2.8-hd/text-to-speech` | Studio-quality narration |
| `minimax/speech-2.8-turbo/text-to-speech` | Fast, low cost |
| `alibaba/qwen-3-tts/text-to-speech` | Chinese and English |
## Prompt tips
- Speech is billed by length; quote the full script before generating.
- Pick the voice from the schema's voice list and state language, pace and emotion.
- Split long scripts into chapters so a single failure does not waste the whole read.
- Do not clone or imitate a real person's voice without their documented consent.
## Setup and cost
Requires Python 3.8+ and a PopNow API key in `POPNOW_API_KEY`. Create a dedicated key at https://popnow.ai/api/console/keys and restrict its models, IPs and spending caps. Keep the key in the agent's secret or environment settings: never ask for it in chat, pass it as a command argument