The speech engine every voice tool in the app shares: text to speech, AI podcast and multi-speaker voiceover all run on it.

Voices are a layer under it rather than models beside it — standard voices on our own engine, Pro voices on ElevenLabs, and cloned voices in the same list.

Strengths

Multi-speaker dialogue, with emotion and tone control
Streaming output
Three voice tools share one voice library

Limitations

Available languages and quality follow the voice you pick, not the model

Capabilities

Capability	Value
Text to speech	Yes
Multi-speaker	Yes
Emotion	Yes
Streaming	Yes
Voice acting	No
Voice clone	No

How it is billed

按音频时长，约 4 积分 / 分钟

No standard price for this model yet.

Alternatives

Seed AudioWhen you want a performance rather than a reading.
Voice CloneWhen you want your own voice.

Call it

# Set LISTENHUB_API_KEY firstcurl -X POST "https://api.marswave.ai/openapi/v1/tts" \-H "Authorization: Bearer $LISTENHUB_API_KEY" \-H "Content-Type: application/json" \-d '{"input": "Hello, welcome to ListenHub text-to-speech.","voice": "EN-Man-General-01","response_format": "mp3","speed": 1.25}'