AI Podcast

AI Podcast synthesizes a multi-role script into a multi-speaker conversation, with per-role voices, background music, subtitles, and single/multi-track output. Async task; poll for status after submitting.

Base URL: https://api.aiclonevoicefree.com | Auth: Authorization: Bearer sk_...

`POST /api/v2/voice/podcast`

Field	Type	Required	Notes
`mode`	string	✅	`auto` (generate script from topic) / `manual` (bring your own segments) / `from_db` (reuse a script)
`topic`	string	⬜	Topic for auto mode
`language`	string	⬜	`zh` / `en`
`roles`	object[]	✅	Role list (below)
`segments`	object[]	⬜	Required in manual mode; per-line text + voice (below)
`reference_podcast_id`	string	⬜	Script id reused in from_db mode
`background`	object	⬜	Background music: `intro_url` / `background_url` / `intro_volume` / `background_volume`
`pause_ms`	int	⬜	Pause between segments (ms)
`tts_model`	string	⬜	TTS model, defaults to server config
`single_track`	bool	⬜	Return per-role timeline-aligned tracks (handy for video editing)
`generate_subtitle`	bool	⬜	Generate SRT subtitles

roles[]: { name, voice_id, audio_url (reference), volume, model (optional per-role override) } segments[]: { text, voice_id, audio_url, role, speed_ratio, pitch_ratio, volume_ratio, emotion_mode, emotion_vector, emotion_text, pause_ms_after }

Billing

By synthesized character count: CJK chars 2 credits each, others 1 credit each, settled on completion. 402 at submit if insufficient.

Example (manual mode)

curl -X POST https://api.aiclonevoicefree.com/api/v2/voice/podcast \
  -H "Authorization: Bearer sk_your_api_key" \
  -H "Content-Type: application/json" \
  -d '{
    "mode": "manual",
    "language": "en",
    "roles": [
      { "name": "Host",  "audio_url": "https://your-cdn.com/host.wav" },
      { "name": "Guest", "audio_url": "https://your-cdn.com/guest.wav" }
    ],
    "segments": [
      { "role": "Host",  "audio_url": "https://your-cdn.com/host.wav",  "text": "Welcome to the show." },
      { "role": "Guest", "audio_url": "https://your-cdn.com/guest.wav", "text": "Glad to be here." }
    ],
    "generate_subtitle": true
  }'

Response 202 → { "task_id": "...", "status": "pending", "capability": "voice", "action": "multi-segment" }

Getting the result

Poll GET /api/v2/tasks/{task_id}; audioUrl is the merged track and srtUrl the subtitle (if enabled). See also AI Dubbing.

AI Podcast

POST /api/v2/voice/podcast

Billing

Example (manual mode)

Getting the result

On this page

`POST /api/v2/voice/podcast`