SoulX Podcast API

Open-source voice model for long-form, multi-speaker podcast dialogue with paralinguistic control (laughter, sighs) and zero-shot voice cloning.

Soul AI Lab Audio Generation Released Oct 29, 2025 Native Inference

About SoulX Podcast

Open-source voice model for long-form, multi-speaker podcast dialogue with paralinguistic control (laughter, sighs) and zero-shot voice cloning.

Also known as Soul AI Lab SoulX Podcast

voice cloning multi speaker dialect podcast

SoulX Podcast specs

Model ID
soulx-podcast
Author
Soul AI Lab
Category
Audio Generation
Released
Oct 29, 2025
Input
TextAudio
Output
Audio
Endpoints
POST/v1/audio/speech
Alternate model IDs
soul-ai-lab/soulx-podcast

SoulX Podcast API pricing

Live pay-as-you-go rates from the EmpirioLabs catalog. You can also choose a plan with weekly allowances.

Type
Spec
Rate
Base
per 1k characters, minimum 700 characters per request
$0.015
Dialect
per 1k characters, minimum 700 characters per request
$0.015
Compare on the full pricing page

How to call the SoulX Podcast API

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
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.mp3
Python
import 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)
Full SoulX Podcast API reference

SoulX Podcast API parameters

Request parameters supported by the SoulX Podcast API on EmpirioLabs. Defaults apply when a field is omitted.

ParameterTypeDefaultRange / valuesDescription
inputstring--Podcast script. Use [S1] / [S2] / [S3] / [S4] tags or 'Speaker N:' lines for multi-speaker. Paralinguistic tags supported: <|laughter|>, <|sigh|>, <|breath|>, <|cough|>.
voice_modelenumbasebase, dialectbase: English + Mandarin. dialect: adds Sichuan, Henan, and Cantonese.
voice_s1enumarthurarthur, james, lj, xiaomei, zhigang, custom_s1Voice for [S1]. lj = Emma. custom_s1 requires voice_s1_audio_url.
voice_s2enumljarthur, james, lj, xiaomei, zhigang, custom_s2Voice for [S2]. lj = Emma.
voice_s3enumjamesarthur, james, lj, xiaomei, zhigang, custom_s3Voice for [S3].
voice_s4enumxiaomeiarthur, james, lj, xiaomei, zhigang, custom_s4Voice for [S4].
voice_s1_audio_urlstring--Reference audio URL for [S1] custom voice cloning: a recording of up to 30 seconds in which the speaker reads this consent statement aloud in English, in their own...
voice_s2_audio_urlstring--Reference audio URL for [S2] custom voice cloning: a recording of up to 30 seconds in which the speaker reads this consent statement aloud in English, in their own...
voice_s3_audio_urlstring--Reference audio URL for [S3] custom voice cloning: a recording of up to 30 seconds in which the speaker reads this consent statement aloud in English, in their own...
voice_s4_audio_urlstring--Reference audio URL for [S4] custom voice cloning: a recording of up to 30 seconds in which the speaker reads this consent statement aloud in English, in their own...
temperaturenumber0.60.1 to 2Sampling temperature.
top_kinteger1001 to 500Top-k sampling cap.
top_pnumber0.90.1 to 1Nucleus sampling.
repetition_penaltynumber1.251 to 2Higher values discourage repeated phrasing.
2 more parameters in the docs

Good to know

Open-source voice model for long-form, multi-speaker podcast dialogue with paralinguistic control and zero-shot voice cloning.

Billed per character, with a minimum of 700 characters per request.

SoulX Podcast API: common questions

How much does the SoulX Podcast API cost?

On EmpirioLabs, SoulX Podcast is billed pay as you go: Base $0.015 per 1k characters, minimum 700 characters per request; Dialect $0.015 per 1k characters, minimum 700 characters per request. You can also choose a plan with weekly allowances. The live rate card on this page always matches what the API charges.

What inputs and outputs does SoulX Podcast support?

SoulX Podcast takes Text, Audio as input and returns Audio.

Which endpoint does SoulX Podcast use?

SoulX Podcast is served through POST /v1/audio/speech on api.empiriolabs.ai with standard bearer-token authentication.

What is the model ID for SoulX Podcast?

Send soulx-podcast as the model in your request. The alternate IDs soul-ai-lab/soulx-podcast also work.

When was SoulX Podcast released?

Soul AI Lab released SoulX Podcast on Oct 29, 2025.

Can I try SoulX Podcast in the browser before integrating?

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.

How do I get a SoulX Podcast API key?

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. You can also choose a plan with weekly allowances.

Ready to use better endpoints?

Check out our pricing or reach out if you want your own model deployed on our stack.