开源语音模型,用于长形,多语种播客对话,配有准语言控制(笑声,叹息)和零镜头语音克隆.
Soul AI Lab音频生成发布日期 Oct 29, 2025原生推理开源语音模型,用于长形,多语种播客对话,配有准语言控制(笑声,叹息)和零镜头语音克隆.
也称为 Soul AI Lab SoulX Podcast, SoulX-Podcast
soulx-podcastPOST /v1/audio/speechLive pay-as-you-go rates from the EmpirioLabs catalog. You are billed only for what you use, with no monthly minimum.
SoulX Podcast serves speech through POST /v1/audio/speech and returns playable audio. Send the text to speak as input with the model id soulx-podcast. Get an API key from the EmpirioLabs dashboard.
curl https://api.empiriolabs.ai/v1/audio/speech \
-H "Authorization: Bearer $EMPIRIOLABS_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "soulx-podcast",
"input": "Welcome to EmpirioLabs. Your build just finished."
}' \
--output speech.mp3import requests
response = requests.post(
"https://api.empiriolabs.ai/v1/audio/speech",
headers={"Authorization": "Bearer YOUR_EMPIRIOLABS_API_KEY"},
json={"model": "soulx-podcast", "input": "Welcome to EmpirioLabs."},
)
with open("speech.mp3", "wb") as f:
f.write(response.content)Request parameters supported by the SoulX Podcast API on EmpirioLabs. Defaults apply when a field is omitted.
| 参数 | 类型 | 默认 | 范围 / 值 | 描述 |
|---|---|---|---|---|
| input | string | - | - | Podcast script. Use [S1] / [S2] / [S3] / [S4] tags or 'Speaker N:' lines for multi-speaker. Paralinguistic tags supported: <|laughter|>, <|sigh|>, <|breath|>, <|cough|>. |
| voice_model | enum | base | base, dialect | base: English + Mandarin. dialect: adds Sichuan, Henan, and Cantonese. |
| voice_s1 | enum | arthur | arthur, james, lj, xiaomei, zhigang, custom_s1 | Voice for [S1]. lj = Emma. custom_s1 requires voice_s1_audio_url. |
| voice_s2 | enum | lj | arthur, james, lj, xiaomei, zhigang, custom_s2 | Voice for [S2]. lj = Emma. |
| voice_s3 | enum | james | arthur, james, lj, xiaomei, zhigang, custom_s3 | Voice for [S3]. |
| voice_s4 | enum | xiaomei | arthur, james, lj, xiaomei, zhigang, custom_s4 | Voice for [S4]. |
| voice_s1_audio_url | string | - | - | Reference audio URL for [S1] custom-voice cloning. Speaker must say the consent phrase aloud. |
| voice_s2_audio_url | string | - | - | Reference audio URL for [S2] custom-voice cloning. |
| voice_s3_audio_url | string | - | - | Reference audio URL for [S3] custom-voice cloning. |
| voice_s4_audio_url | string | - | - | Reference audio URL for [S4] custom-voice cloning. |
| temperature | number | 0.6 | 0.1 to 2 | Sampling temperature. |
| top_k | number | 100 | 1 to 500 | Top-k sampling cap. |
| top_p | number | 0.9 | 0.1 to 1 | Nucleus sampling. |
| repetition_penalty | number | 1.25 | 1 to 2 | Higher values discourage repeated phrasing. |
开源语音模型,用于长形,多语种播客对话,配有准语言控制和零镜头语音克隆.
On EmpirioLabs, SoulX Podcast is billed pay as you go: 基础 $0.015 每1k个字符; 对话框 $0.015 每1k个字符. The live rate card on this page always matches what the API charges.
SoulX Podcast is served through POST /v1/audio/speech on api.empiriolabs.ai with standard bearer-token authentication.
Yes. The EmpirioLabs playground runs SoulX Podcast in the browser with the same parameters the API exposes, so you can test prompts before writing code.
Create an EmpirioLabs account, then generate a key under API Keys in the dashboard. Billing is pay-as-you-go credits, so you only pay for the requests you make.
Check out our pricing or reach out if you want your own model deployed on our stack.
