AI Voice Cloning Assistant

25 voice clone podcast

by minhnv0807 · MIT license · ★ 599 on GitHub

25 voice clone podcast cover

Dung khi mot CA NHAN can AM THANH bang AI — clone giong noi, lam podcast, audiobook, voiceover cho video: 3 use case gom voiceover ngan cho TikTok va Reels, podcast 30-60 phut, audiobook; quy trinh thu mau giong, chinh cam xuc va toc…

---
name: 25-voice-clone-podcast
description: "Dung khi mot CA NHAN can AM THANH bang AI — clone giong noi, lam podcast, audiobook, voiceover cho video: 3 use case gom voiceover ngan cho TikTok va Reels, podcast 30-60 phut, audiobook; quy trinh thu mau giong, chinh cam xuc va toc do, cong bo dung luat, tai su dung 1 podcast thanh 10 clip ngan. Kich hoat khi user nhac 'voice clone', 'clone giong noi', 'ElevenLabs', 'lam podcast', 'audio AI', 'voiceover AI', 'ngai thu am moi ngay', 'cat podcast ra clip ngan'. Khong dung cho — video co hinh anh nguoi hoac avatar thi dung skill 24-ai-avatar-production; viet loi thoai va hook noi thi dung skill 04-script-video; viet bai dai dang chu thi dung skill 26-thought-leadership-content."
metadata:
  version: 1.0.1
  category: content
license: MIT
triggers:
  - "voice clone"
  - "ElevenLabs giong noi"
  - "podcast AI"
  - "audio AI"
  - "Descript voice"
  - "Riverside podcast"
  - "voiceover AI"
related:
  - 24-ai-avatar-production
  - 26-thought-leadership-content

Overview

Audio AI la cong nghe tao ra giong noi nhan tao gan giong nguoi that — tu sample giong cua ban, AI hoc va tao ra giong nhan ban (voice clone). Ban viet text → AI doc thay (Text-to-Speech).

Manual install (npx, ZIP)
Claude Codenpx skills add minhnv0807/ai-business-skills --skill 25-voice-clone-podcast -g -a claude-code
Claude Code (degit)npx degit minhnv0807/ai-business-skills/modules/personal-branding/vi/25-voice-clone-podcast#master ~/.claude/skills/25-voice-clone-podcast
Claude.ai / desktopZip the folder and upload it under Settings → Capabilities → Skills.
Codex, Cursor, other agentsPoint them at SKILL.md. The other files are plain text.

Connects with Agent Alley MCP · agentalley.io/mcp

Files included

  • SKILL.md15.4 KB
Read SKILL.md here
minhnv0807/master1 file shown
SKILL.md
Show the full text386 lines

Voice Clone & Podcast — Audio AI cho Personal Brand

Skill nay tap trung vao audio AI — voice clone, podcast, audiobook, voiceover. Bo sung cho 24-ai-avatar-production (video) — ket hop ca 2 de phu het content stack.


1. Cho nguoi moi (Newbie Guide)

Audio AI la gi va khac voi video AI?

Audio AI la cong nghe tao ra giong noi nhan tao gan giong nguoi that — tu sample giong cua ban, AI hoc va tao ra giong nhan ban (voice clone). Ban viet text → AI doc thay (Text-to-Speech).

Khac biet voi video AI:

  • Video AI (skill 24): Tao video co hinh + giong → lam talking head, social video
  • Audio AI (skill nay): Chi tao giong → lam podcast, audiobook, voiceover, narration
Khi nao dung audio AI thay vi quay video?
Tinh huong Chon audio AI Chon video AI
Noi dung dai (>10 phut) YES — podcast format NO — too long for video
Khong muon len hinh YES NO
Can tao volume content nhanh YES — 1 podcast = 10 short YES nhung ton hon
Audience nghe khi lai xe / tap gym YES NO
Can visual de demo NO YES
Personal brand thought leader YES — podcast = authority YES — neu da co face brand
Tools chinh
  • ElevenLabs: Tot nhat the gioi cho voice clone — VN voice tot, EN voice xuat sac
  • Vbee: Tot nhat tieng Viet — natural intonation, da giong vung mien
  • HeyGen Voice: Combo voi avatar HeyGen — workflow lien tuc voice + video
  • Descript: AI editing — cat audio bang text, voice clone (Overdub)
  • Riverside: Podcast recording — chat luong studio, AI Magic Clips repurpose
Mat bao lau / chi phi?
Cong viec Thoi gian Chi phi (USD/thang)
Voice clone setup 30-60 phut $5-22 (ElevenLabs Starter/Pro)
Voiceover 60s (TikTok) 5-10 phut $5-22
Podcast 30 phut (solo) 1-2 gio $22-99 (ElevenLabs + Riverside)
Audiobook 1 chuong (15 phut) 30-45 phut $22-99
Repurpose 1 podcast → 10 clip 1-2 gio $0-30 (Descript/Opus)
5 loi thuong gap
  1. Giong AI nghe robot: Sample qua ngan hoac don dieu. Fix: thu lai 3-5 phut, doc nhieu cam xuc khac nhau (vui, buon, nghiem tuc).
  2. Phat am sai tu tieng Viet: ElevenLabs van con yeu vai tu Han-Viet. Fix: dung Vbee cho VN content, hoac sua tu bang phonetic spelling.
  3. Audio bi clipping (vo tieng): Levels qua cao. Fix: target -3dB peak, -16 LUFS loudness.
  4. Bi noise/echo: Phong khong tieu am. Fix: thu am phong nho co rem, treo chan, hoac dung NVIDIA Broadcast / Krisp khu noise.
  5. Podcast nghe chan: Khong co edit, qua nhieu "um a". Fix: Descript auto-remove filler words, them background music nhe (-20dB).

2. Thu thap thong tin

Hoi toi da 4 cau truoc khi bat dau:

  1. Use case chinh? Voiceover ngan (TikTok/Reels) / Podcast 30-60 phut / Audiobook?
  2. Ngon ngu? Tieng Viet / Tieng Anh / Song ngu (VN-EN)?
  3. Thoi luong tong? <60s / 5-30 phut / 30-60 phut / >60 phut (audiobook)?
  4. Ngan sach tier? Free ($0) / Starter ($5-22) / Pro ($22-99) / Business ($99+)?

Dua tren 4 cau tra loi, chon use case + tool stack phu hop.


3. Voice clone setup

Yeu cau sample
Tieu chi Yeu cau toi thieu Toi uu
Thoi luong 1 phut (Free tier) 3-5 phut (Pro tier)
Phong Yen tinh, khong vang Treo chan, rem, sach hap thu am
Mic iPhone + tai nghe co mic Condenser mic (AT2020, $80-100)
Distance 20-30cm 15-20cm voi pop filter
Format MP3 128kbps WAV 44.1kHz
Noi dung 1 doan van da chuan bi 3 doan van: business / casual / emotional

Reference day du: references/voice-clone-prompts-vn.md — 3 sample script theo vung giong (Bac/Trung/Nam) va 3 topic (business/lifestyle/educational).

Tool comparison
Tool VN voice clone Gia/thang Setup time Best for
ElevenLabs Pro Tot (8/10) $22 30 phut Multi-language, content creator
HeyGen Voice Trung binh (6/10) Bundle voi avatar 15 phut Combo voi video AI
Vbee Pro Xuat sac (9.5/10) 199K-499K VND 45 phut VN-only, broadcast TTS
Descript Overdub Trung binh (6/10) $24 (Hobbyist) 30 phut Podcast editing
Resemble.ai Trung binh (7/10) $30 1 gio API integration, custom

Khuyen nghi:

  • VN-only content: Vbee Pro (tot nhat phat am tieng Viet)
  • Multi-lang (VN + EN): ElevenLabs Pro
  • Combo voi video: HeyGen (1 platform — voice + avatar)
THOA THUAN SU DUNG VOICE CLONE

Toi, [Ho ten], CMND/CCCD: [so], dong y cho [Brand/Cong ty]:
1. Su dung sample giong noi cua toi de tao voice clone AI
2. Su dung voice clone trong [pham vi: noi bo / quang cao / podcast / etc.]
3. Thoi han: [tu DD/MM/YYYY den DD/MM/YYYY]
4. Quyen rut lai: Toi co quyen yeu cau xoa voice clone bat ky luc nao
   bang van ban, brand co 7 ngay de xoa hoan toan.
5. Cong khai: Brand cam ket disclose "AI voice" theo quy tac VN.

Ky ten: ____________  Ngay: ____________

4. 3 use case rieng

Use case A: Voiceover ngan TikTok/Reels (Energetic)

Spec:

  • Thoi luong: 15-60s
  • Pace: Fast (180-220 words/phut) — gioi tre VN
  • Tone: Energetic, high-pitch, exciting
  • Audio levels: -14 LUFS (TikTok loudness), peak -1dB
  • CTA: Ro rang trong 5s cuoi

Script template (30s):

[HOOK 0-3s] "Ban co biet [stat shocking]?"
[PROBLEM 3-10s] "Hau het moi nguoi van dang [vong xoay sai]"
[SOLUTION 10-22s] "Toi da thu [phuong phap], va day la 3 dieu..."
[PAYOFF 22-27s] "Ket qua: [so cu the]"
[CTA 27-30s] "Comment 'YES' de minh gui chi tiet"

Voice settings (ElevenLabs):

  • Stability: 35-45 (low — cho phep variation)
  • Similarity: 75-85
  • Style: 50-65 (boost expressiveness)
  • Speaker Boost: ON
Use case B: Podcast 30-60 phut (Conversational)

Cau truc:

  • Intro (1-2 phut): Hook + introduce topic + welcome listeners
  • Body (25-50 phut): 3-5 main segments, moi segment 5-10 phut
  • Ad slot (optional): Sau intro 3-5 phut, hoac giua body
  • Outro (1-2 phut): Recap key points + CTA + thanks

Pacing:

  • Conversational pace: 140-160 words/phut
  • Pause 1-2s sau cau quan trong (cho audience tieu hoa)
  • Doan chuyen segment: pause 2-3s + audio sting

Sound design:

  • Background music: -25 to -30 dB (rat nhe, khong at giong)
  • Stings/transitions: -15 dB, dai 1-2s
  • Voice levels: -16 LUFS (podcast standard), peak -1dB

Voice settings (ElevenLabs):

  • Stability: 60-75 (cao — consistent qua 30+ phut)
  • Similarity: 85-95
  • Style: 30-40 (natural, khong qua expressive)
  • Speaker Boost: ON
Use case C: Audiobook (Mid-tempo)

Cau truc:

  • Chapter intro: "Chuong [X]: [Tieu de]" — pause 2s
  • Chapter body: 10-20 phut/chuong, doan paragraph cach pause 1s
  • Chapter end: Pause 3s truoc khi chuyen chapter

Pacing:

  • Mid-tempo: 150-170 words/phut
  • Breath control: pause tu nhien moi 2-3 cau
  • Doan dialogue: thay doi tone giong nhan vat (neu fiction)

Consistency check (quan trong nhat):

  • Render thu chapter 1 va chapter 5 → so sanh giong → phai giong nhau 95%+
  • Neu khac biet: re-clone voi sample dai hon (5+ phut)
  • Pronunciation guide: lap database ten rieng + cach phat am dac biet

Voice settings (Vbee, neu VN):

  • Voice: "Nu mien Bac chuyen nghiep" hoac "Nam mien Bac am tinh"
  • Speed: 0.95x (cham hon mot chut)
  • Pitch: Default
  • Pause length: 1.2x (dai hon mot chut)

5. Tool comparison VN

Tool Gia/thang VN voice native EN voice Setup Pros Cons Best for
ElevenLabs $5-99 8/10 10/10 30 phut Multi-lang, voice clone tot VN phat am vai tu kho Multi-lang creator
Vbee 199K-1.5M VND 9.5/10 6/10 45 phut VN tot nhat, da giong vung Khong manh EN VN-only audio
HeyGen Voice Bundle voi avatar 6/10 8/10 15 phut Combo voi avatar Voice clone don dieu Combo voi video
Descript $24-30 6/10 9/10 30 phut Audio editing manh VN voice yeu Podcast editing
Riverside $19-29 n/a (recording) n/a 5 phut Studio quality recording Khong phai TTS Live podcast
Murf $29-79 7/10 9/10 30 phut 120+ voice library Voice clone gioi han Corporate voiceover
PlayHT $39-99 7/10 9.5/10 30 phut API tot, instant clone UI kho Developer/API
Resemble.ai $30-99 7/10 9/10 1 gio Custom emotion control Hoc cao Brand custom voice

Combo khuyen nghi 2025-2026:

  • VN solo creator: Vbee Pro (199K) + Riverside Free + Descript Hobbyist ($24)
  • Multi-lang creator: ElevenLabs Pro ($22) + Riverside Standard ($19) + Descript Pro ($30)
  • Brand/Agency: ElevenLabs Creator ($99) + Vbee Business + Riverside Pro ($29)

6. Workflow 1-on-1 podcast voi AI co-host

Use case: Solo podcaster muon co conversation, khong tim duoc co-host that. AI co-host = giong AI thu 2 dong vai dong host, hoi cau + ban tra loi.

Setup prompt engineering cho AI personality

Buoc 1: Dinh nghia personality cua AI co-host

Ten: [Ten AI co-host]
Tinh cach: Tro mo, hay hoi sau, doi khi hai huoc nhe
Vai tro: Dat cau hoi cho host, khong tu noi qua nhieu
Phong cach noi: Casual, tu nhien, dung "minh/ban" (khong "toi/anh")
Cap do kien thuc: Trung binh — dat cau hoi nhu listener
Cau cam thuong dung: "Wow, hay quoc!", "Vay nghia la sao?", "Cu the hon nha?"

Buoc 2: Tao voice clone rieng cho AI co-host

  • Su dung giong khac voi host (vd: nu vs nam, hoac giong vung khac)
  • Voice clone tu mot nguoi than dong y, hoac dung giong AI co san trong ElevenLabs

Buoc 3: Tool stack

  • ElevenLabs: Tao giong AI co-host (voice clone)
  • Riverside: Recording host noi (live)
  • Descript: Edit + ghep AI co-host vao (text-to-audio)
Script template (Q&A format)
[INTRO]
Host: Chao moi nguoi, hom nay minh va [AI co-host] se ban ve...
AI co-host: Chao cac ban, minh la [ten]. Hom nay minh muon hieu sau ve [topic]
            tu goc nhin cua [host]. Bat dau thoi!

[BODY — 5-7 cap Q&A]
AI co-host: [Hoi cau 1 — broad question]
Host: [Tra loi 2-3 phut]
AI co-host: [Hoi follow-up sau hon]
Host: [Tra loi voi vi du cu the]
... lap lai 5-7 lan ...

[OUTRO]
AI co-host: Cam on [host] da chia se. Toi nhat ma minh hoc duoc la...
Host: Cam on [AI co-host]. Cac ban con cau hoi gi, comment ben duoi...

Tip: Viet truoc 7-10 cau hoi cua AI co-host trong document, host tra loi luot. Sau do generate audio cua AI co-host bang ElevenLabs, ghep vao bang Descript.


7. Repurpose pipeline 1:10 (1 podcast → 10 short clip)

Workflow tong quan
[1] Record podcast 60 phut (Riverside)
        ↓
[2] Transcript tu dong (Descript / Riverside)
        ↓
[3] Identify hooks (10-15 cau hay)
        ↓
[4] Cut clips 30-60s moi cau (Opus Clip / Descript)
        ↓
[5] Add captions (auto-caption)
        ↓
[6] Distribute ra 4 nen tang
Cach identify hooks (cau hay)

Tim trong transcript nhung cau co dac diem:

  • Bold statement: "Toi nghi 90% nguoi VN dang lam sai dieu nay"
  • Counter-intuitive: "Tang gia san pham thuc su lai tang doanh thu"
  • Specific number: "Toi tu 0 len 1 ty trong 6 thang"
  • Personal story: "Lan dau khoi nghiep toi mat 200 trieu"
  • Actionable tip: "3 buoc cu the de bat dau ngay hom nay"

Target: 10-15 hook cho 1 podcast 60 phut. Loc lai 10 clip ngon nhat.

Tool stack
  • Descript: Auto-clip — chon cau, cat ra clip ngon (free tier 1 gio/thang)
  • Opus Clip: AI tu dong tim viral moments + auto-format dung/ngang ($19-99)
  • Riverside Magic Clips: Built-in feature trong Riverside Pro ($29)
  • CapCut + ChatGPT: Manual nhung mien phi — paste transcript, ChatGPT phan tich hooks
Distribution 4 nen tang
Nen tang Format Thoi luong Caption Bonus
TikTok 9:16 (1080×1920) 30-60s Bold caption tren Trend audio overlay (volume thap)
Instagram Reels 9:16 15-90s Subtitle dep, font sans-serif Cover image dep
YouTube Shorts 9:16 <60s Auto-caption YouTube Title chua keyword
LinkedIn audio 1:1 (square video voi audio) 60-120s Caption ben duoi Doc thread bai dai (carousel)

Pro tip: Moi clip = 1 platform rieng, dung khac caption + cover image. Tang reach.


8. QA audio + Disclosure

5 QA criteria
  1. Clarity (10 diem): Giong ro, khong bi ren, khong lap. Test: phat tren loa dien thoai → van nghe ro
  2. No clipping (10 diem): Peak khong vuot -1dB. Tool check: Audacity, Adobe Audition, Reaper
  3. No background noise (10 diem): Khong tieng quat, xe co, hang xom. Tool: Krisp, NVIDIA Broadcast, Adobe Enhance Speech
  4. Consistent volume (10 diem): Loudness on dinh -16 LUFS (podcast) hoac -14 LUFS (TikTok). Tool: Loudness meter trong DAW
  5. Natural pauses (10 diem): Pause hop ly, khong robot. Manual review: nghe lai 3 lan

Pass: 40+/50 diem. <40 = re-render hoac re-record.

VN disclosure — khi nao bat buoc
Tinh huong Disclosure Vi tri
Quang cao thuong mai BAT BUOC Caption + cuoi audio ("Audio nay su dung voice clone AI")
Podcast personal brand NEN — minh bach Episode description
Audiobook fiction KHONG bat buoc Optional — credits cuoi
Tin tuc/giao duc BAT BUOC Dau audio + caption
Noi dung noi bo cong ty KHONG bat buoc n/a

Template disclosure caption:

Audio nay su dung cong nghe voice clone AI
(ElevenLabs / Vbee / [tool ten]). Noi dung do [Ten ban] viet va duyet.

Reference day du: references/ai-video-disclosure-vn.md — Nghi dinh 147/2024, 3 tang disclose, va template cho tung tinh huong (cung ap dung cho audio).


9. Checklist chat luong

Truoc khi xuat ban audio:

  • Sample voice clone 3-5 phut, phong yen tinh
  • Consent form ky ten (neu clone giong nguoi khac)
  • Use case dung: voiceover (energetic) / podcast (conversational) / audiobook (mid-tempo)
  • Voice settings phu hop use case (Stability/Similarity/Style)
  • Loudness chuan: -14 LUFS (TikTok) / -16 LUFS (podcast/audiobook)
  • Peak khong vuot -1dB (no clipping)
  • No background noise (Krisp/NVIDIA Broadcast pass)
  • Pacing dung: 180-220 wpm (TikTok) / 140-160 wpm (podcast) / 150-170 wpm (audiobook)
  • QA Score 40+/50
  • Disclosure caption (neu commercial use)
  • Repurpose plan: 1 podcast → 10 clip distribute 4 platform
1---
2name: 25-voice-clone-podcast
3description: "Dung khi mot CA NHAN can AM THANH bang AI — clone giong noi, lam podcast, audiobook, voiceover cho video: 3 use case gom voiceover ngan cho TikTok va Reels, podcast 30-60 phut, audiobook; quy trinh thu mau giong, chinh cam xuc va toc do, cong bo dung luat, tai su dung 1 podcast thanh 10 clip ngan. Kich hoat khi user nhac 'voice clone', 'clone giong noi', 'ElevenLabs', 'lam podcast', 'audio AI', 'voiceover AI', 'ngai thu am moi ngay', 'cat podcast ra clip ngan'. Khong dung cho — video co hinh anh nguoi hoac avatar thi dung skill 24-ai-avatar-production; viet loi thoai va hook noi thi dung skill 04-script-video; viet bai dai dang chu thi dung skill 26-thought-leadership-content."
4metadata:
5 version: 1.0.1
6 category: content
7license: MIT
8triggers:
9 - "voice clone"
10 - "ElevenLabs giong noi"
11 - "podcast AI"
12 - "audio AI"
13 - "Descript voice"
14 - "Riverside podcast"
15 - "voiceover AI"
16related:
17 - 24-ai-avatar-production
18 - 26-thought-leadership-content
19 - references/voice-clone-prompts-vn
20 - references/ai-video-disclosure-vn
21---
22 
23# Voice Clone & Podcast — Audio AI cho Personal Brand
24 
25> **Skill nay tap trung vao audio AI** — voice clone, podcast, audiobook, voiceover.
26> Bo sung cho `24-ai-avatar-production` (video) — ket hop ca 2 de phu het content stack.
27 
28---
29 
30## 1. Cho nguoi moi (Newbie Guide)
31 
32### Audio AI la gi va khac voi video AI?
33 
34Audio AI la cong nghe tao ra giong noi nhan tao gan giong nguoi that — tu sample
35giong cua ban, AI hoc va tao ra giong nhan ban (voice clone). Ban viet text →
36AI doc thay (Text-to-Speech).
37 
38**Khac biet voi video AI:**
39- Video AI (skill 24): Tao video co hinh + giong → lam talking head, social video
40- Audio AI (skill nay): Chi tao giong → lam podcast, audiobook, voiceover, narration
41 
42### Khi nao dung audio AI thay vi quay video?
43 
44| Tinh huong | Chon audio AI | Chon video AI |
45|-----------|---------------|---------------|
46| Noi dung dai (>10 phut) | YES — podcast format | NO — too long for video |
47| Khong muon len hinh | YES | NO |
48| Can tao volume content nhanh | YES — 1 podcast = 10 short | YES nhung ton hon |
49| Audience nghe khi lai xe / tap gym | YES | NO |
50| Can visual de demo | NO | YES |
51| Personal brand thought leader | YES — podcast = authority | YES — neu da co face brand |
52 
53### Tools chinh
54 
55- **ElevenLabs:** Tot nhat the gioi cho voice clone — VN voice tot, EN voice xuat sac
56- **Vbee:** Tot nhat tieng Viet — natural intonation, da giong vung mien
57- **HeyGen Voice:** Combo voi avatar HeyGen — workflow lien tuc voice + video
58- **Descript:** AI editing — cat audio bang text, voice clone (Overdub)
59- **Riverside:** Podcast recording — chat luong studio, AI Magic Clips repurpose
60 
61### Mat bao lau / chi phi?
62 
63| Cong viec | Thoi gian | Chi phi (USD/thang) |
64|-----------|-----------|----------------------|
65| Voice clone setup | 30-60 phut | $5-22 (ElevenLabs Starter/Pro) |
66| Voiceover 60s (TikTok) | 5-10 phut | $5-22 |
67| Podcast 30 phut (solo) | 1-2 gio | $22-99 (ElevenLabs + Riverside) |
68| Audiobook 1 chuong (15 phut) | 30-45 phut | $22-99 |
69| Repurpose 1 podcast → 10 clip | 1-2 gio | $0-30 (Descript/Opus) |
70 
71### 5 loi thuong gap
72 
731. **Giong AI nghe robot:** Sample qua ngan hoac don dieu. Fix: thu lai 3-5 phut, doc nhieu cam xuc khac nhau (vui, buon, nghiem tuc).
742. **Phat am sai tu tieng Viet:** ElevenLabs van con yeu vai tu Han-Viet. Fix: dung Vbee cho VN content, hoac sua tu bang phonetic spelling.
753. **Audio bi clipping (vo tieng):** Levels qua cao. Fix: target -3dB peak, -16 LUFS loudness.
764. **Bi noise/echo:** Phong khong tieu am. Fix: thu am phong nho co rem, treo chan, hoac dung NVIDIA Broadcast / Krisp khu noise.
775. **Podcast nghe chan:** Khong co edit, qua nhieu "um a". Fix: Descript auto-remove filler words, them background music nhe (-20dB).
78 
79---
80 
81## 2. Thu thap thong tin
82 
83Hoi toi da 4 cau truoc khi bat dau:
84 
851. **Use case chinh?** Voiceover ngan (TikTok/Reels) / Podcast 30-60 phut / Audiobook?
862. **Ngon ngu?** Tieng Viet / Tieng Anh / Song ngu (VN-EN)?
873. **Thoi luong tong?** <60s / 5-30 phut / 30-60 phut / >60 phut (audiobook)?
884. **Ngan sach tier?** Free ($0) / Starter ($5-22) / Pro ($22-99) / Business ($99+)?
89 
90> Dua tren 4 cau tra loi, chon use case + tool stack phu hop.
91 
92---
93 
94## 3. Voice clone setup
95 
96### Yeu cau sample
97 
98| Tieu chi | Yeu cau toi thieu | Toi uu |
99|----------|---------------------|--------|
100| Thoi luong | 1 phut (Free tier) | 3-5 phut (Pro tier) |
101| Phong | Yen tinh, khong vang | Treo chan, rem, sach hap thu am |
102| Mic | iPhone + tai nghe co mic | Condenser mic (AT2020, $80-100) |
103| Distance | 20-30cm | 15-20cm voi pop filter |
104| Format | MP3 128kbps | WAV 44.1kHz |
105| Noi dung | 1 doan van da chuan bi | 3 doan van: business / casual / emotional |
106 
107> **Reference day du:** `references/voice-clone-prompts-vn.md` — 3 sample script
108> theo vung giong (Bac/Trung/Nam) va 3 topic (business/lifestyle/educational).
109 
110### Tool comparison
111 
112| Tool | VN voice clone | Gia/thang | Setup time | Best for |
113|------|----------------|-----------|------------|----------|
114| **ElevenLabs Pro** | Tot (8/10) | $22 | 30 phut | Multi-language, content creator |
115| **HeyGen Voice** | Trung binh (6/10) | Bundle voi avatar | 15 phut | Combo voi video AI |
116| **Vbee Pro** | Xuat sac (9.5/10) | 199K-499K VND | 45 phut | VN-only, broadcast TTS |
117| **Descript Overdub** | Trung binh (6/10) | $24 (Hobbyist) | 30 phut | Podcast editing |
118| **Resemble.ai** | Trung binh (7/10) | $30 | 1 gio | API integration, custom |
119 
120**Khuyen nghi:**
121- **VN-only content:** Vbee Pro (tot nhat phat am tieng Viet)
122- **Multi-lang (VN + EN):** ElevenLabs Pro
123- **Combo voi video:** HeyGen (1 platform — voice + avatar)
124 
125### Consent form template
126 
127```
128THOA THUAN SU DUNG VOICE CLONE
129 
130Toi, [Ho ten], CMND/CCCD: [so], dong y cho [Brand/Cong ty]:
1311. Su dung sample giong noi cua toi de tao voice clone AI
1322. Su dung voice clone trong [pham vi: noi bo / quang cao / podcast / etc.]
1333. Thoi han: [tu DD/MM/YYYY den DD/MM/YYYY]
1344. Quyen rut lai: Toi co quyen yeu cau xoa voice clone bat ky luc nao
135 bang van ban, brand co 7 ngay de xoa hoan toan.
1365. Cong khai: Brand cam ket disclose "AI voice" theo quy tac VN.
137 
138Ky ten: ____________ Ngay: ____________
139```
140 
141---
142 
143## 4. 3 use case rieng
144 
145### Use case A: Voiceover ngan TikTok/Reels (Energetic)
146 
147**Spec:**
148- Thoi luong: 15-60s
149- Pace: Fast (180-220 words/phut) — gioi tre VN
150- Tone: Energetic, high-pitch, exciting
151- Audio levels: -14 LUFS (TikTok loudness), peak -1dB
152- CTA: Ro rang trong 5s cuoi
153 
154**Script template (30s):**
155```
156[HOOK 0-3s] "Ban co biet [stat shocking]?"
157[PROBLEM 3-10s] "Hau het moi nguoi van dang [vong xoay sai]"
158[SOLUTION 10-22s] "Toi da thu [phuong phap], va day la 3 dieu..."
159[PAYOFF 22-27s] "Ket qua: [so cu the]"
160[CTA 27-30s] "Comment 'YES' de minh gui chi tiet"
161```
162 
163**Voice settings (ElevenLabs):**
164- Stability: 35-45 (low — cho phep variation)
165- Similarity: 75-85
166- Style: 50-65 (boost expressiveness)
167- Speaker Boost: ON
168 
169### Use case B: Podcast 30-60 phut (Conversational)
170 
171**Cau truc:**
172- **Intro (1-2 phut):** Hook + introduce topic + welcome listeners
173- **Body (25-50 phut):** 3-5 main segments, moi segment 5-10 phut
174- **Ad slot (optional):** Sau intro 3-5 phut, hoac giua body
175- **Outro (1-2 phut):** Recap key points + CTA + thanks
176 
177**Pacing:**
178- Conversational pace: 140-160 words/phut
179- Pause 1-2s sau cau quan trong (cho audience tieu hoa)
180- Doan chuyen segment: pause 2-3s + audio sting
181 
182**Sound design:**
183- Background music: -25 to -30 dB (rat nhe, khong at giong)
184- Stings/transitions: -15 dB, dai 1-2s
185- Voice levels: -16 LUFS (podcast standard), peak -1dB
186 
187**Voice settings (ElevenLabs):**
188- Stability: 60-75 (cao — consistent qua 30+ phut)
189- Similarity: 85-95
190- Style: 30-40 (natural, khong qua expressive)
191- Speaker Boost: ON
192 
193### Use case C: Audiobook (Mid-tempo)
194 
195**Cau truc:**
196- **Chapter intro:** "Chuong [X]: [Tieu de]" — pause 2s
197- **Chapter body:** 10-20 phut/chuong, doan paragraph cach pause 1s
198- **Chapter end:** Pause 3s truoc khi chuyen chapter
199 
200**Pacing:**
201- Mid-tempo: 150-170 words/phut
202- Breath control: pause tu nhien moi 2-3 cau
203- Doan dialogue: thay doi tone giong nhan vat (neu fiction)
204 
205**Consistency check (quan trong nhat):**
206- Render thu chapter 1 va chapter 5 → so sanh giong → phai giong nhau 95%+
207- Neu khac biet: re-clone voi sample dai hon (5+ phut)
208- Pronunciation guide: lap database ten rieng + cach phat am dac biet
209 
210**Voice settings (Vbee, neu VN):**
211- Voice: "Nu mien Bac chuyen nghiep" hoac "Nam mien Bac am tinh"
212- Speed: 0.95x (cham hon mot chut)
213- Pitch: Default
214- Pause length: 1.2x (dai hon mot chut)
215 
216---
217 
218## 5. Tool comparison VN
219 
220| Tool | Gia/thang | VN voice native | EN voice | Setup | Pros | Cons | Best for |
221|------|-----------|-----------------|----------|-------|------|------|----------|
222| **ElevenLabs** | $5-99 | 8/10 | 10/10 | 30 phut | Multi-lang, voice clone tot | VN phat am vai tu kho | Multi-lang creator |
223| **Vbee** | 199K-1.5M VND | 9.5/10 | 6/10 | 45 phut | VN tot nhat, da giong vung | Khong manh EN | VN-only audio |
224| **HeyGen Voice** | Bundle voi avatar | 6/10 | 8/10 | 15 phut | Combo voi avatar | Voice clone don dieu | Combo voi video |
225| **Descript** | $24-30 | 6/10 | 9/10 | 30 phut | Audio editing manh | VN voice yeu | Podcast editing |
226| **Riverside** | $19-29 | n/a (recording) | n/a | 5 phut | Studio quality recording | Khong phai TTS | Live podcast |
227| **Murf** | $29-79 | 7/10 | 9/10 | 30 phut | 120+ voice library | Voice clone gioi han | Corporate voiceover |
228| **PlayHT** | $39-99 | 7/10 | 9.5/10 | 30 phut | API tot, instant clone | UI kho | Developer/API |
229| **Resemble.ai** | $30-99 | 7/10 | 9/10 | 1 gio | Custom emotion control | Hoc cao | Brand custom voice |
230 
231**Combo khuyen nghi 2025-2026:**
232- **VN solo creator:** Vbee Pro (199K) + Riverside Free + Descript Hobbyist ($24)
233- **Multi-lang creator:** ElevenLabs Pro ($22) + Riverside Standard ($19) + Descript Pro ($30)
234- **Brand/Agency:** ElevenLabs Creator ($99) + Vbee Business + Riverside Pro ($29)
235 
236---
237 
238## 6. Workflow 1-on-1 podcast voi AI co-host
239 
240> **Use case:** Solo podcaster muon co conversation, khong tim duoc co-host that.
241> AI co-host = giong AI thu 2 dong vai dong host, hoi cau + ban tra loi.
242 
243### Setup prompt engineering cho AI personality
244 
245**Buoc 1: Dinh nghia personality cua AI co-host**
246```
247Ten: [Ten AI co-host]
248Tinh cach: Tro mo, hay hoi sau, doi khi hai huoc nhe
249Vai tro: Dat cau hoi cho host, khong tu noi qua nhieu
250Phong cach noi: Casual, tu nhien, dung "minh/ban" (khong "toi/anh")
251Cap do kien thuc: Trung binh — dat cau hoi nhu listener
252Cau cam thuong dung: "Wow, hay quoc!", "Vay nghia la sao?", "Cu the hon nha?"
253```
254 
255**Buoc 2: Tao voice clone rieng cho AI co-host**
256- Su dung giong khac voi host (vd: nu vs nam, hoac giong vung khac)
257- Voice clone tu mot nguoi than dong y, hoac dung giong AI co san trong ElevenLabs
258 
259**Buoc 3: Tool stack**
260- **ElevenLabs:** Tao giong AI co-host (voice clone)
261- **Riverside:** Recording host noi (live)
262- **Descript:** Edit + ghep AI co-host vao (text-to-audio)
263 
264### Script template (Q&A format)
265 
266```
267[INTRO]
268Host: Chao moi nguoi, hom nay minh va [AI co-host] se ban ve...
269AI co-host: Chao cac ban, minh la [ten]. Hom nay minh muon hieu sau ve [topic]
270 tu goc nhin cua [host]. Bat dau thoi!
271 
272[BODY — 5-7 cap Q&A]
273AI co-host: [Hoi cau 1 — broad question]
274Host: [Tra loi 2-3 phut]
275AI co-host: [Hoi follow-up sau hon]
276Host: [Tra loi voi vi du cu the]
277... lap lai 5-7 lan ...
278 
279[OUTRO]
280AI co-host: Cam on [host] da chia se. Toi nhat ma minh hoc duoc la...
281Host: Cam on [AI co-host]. Cac ban con cau hoi gi, comment ben duoi...
282```
283 
284**Tip:** Viet truoc 7-10 cau hoi cua AI co-host trong document, host tra loi luot.
285Sau do generate audio cua AI co-host bang ElevenLabs, ghep vao bang Descript.
286 
287---
288 
289## 7. Repurpose pipeline 1:10 (1 podcast → 10 short clip)
290 
291### Workflow tong quan
292 
293```
294[1] Record podcast 60 phut (Riverside)
295 ↓
296[2] Transcript tu dong (Descript / Riverside)
297 ↓
298[3] Identify hooks (10-15 cau hay)
299 ↓
300[4] Cut clips 30-60s moi cau (Opus Clip / Descript)
301 ↓
302[5] Add captions (auto-caption)
303 ↓
304[6] Distribute ra 4 nen tang
305```
306 
307### Cach identify hooks (cau hay)
308 
309Tim trong transcript nhung cau co dac diem:
310- **Bold statement:** "Toi nghi 90% nguoi VN dang lam sai dieu nay"
311- **Counter-intuitive:** "Tang gia san pham thuc su lai tang doanh thu"
312- **Specific number:** "Toi tu 0 len 1 ty trong 6 thang"
313- **Personal story:** "Lan dau khoi nghiep toi mat 200 trieu"
314- **Actionable tip:** "3 buoc cu the de bat dau ngay hom nay"
315 
316> **Target:** 10-15 hook cho 1 podcast 60 phut. Loc lai 10 clip ngon nhat.
317 
318### Tool stack
319 
320- **Descript:** Auto-clip — chon cau, cat ra clip ngon (free tier 1 gio/thang)
321- **Opus Clip:** AI tu dong tim viral moments + auto-format dung/ngang ($19-99)
322- **Riverside Magic Clips:** Built-in feature trong Riverside Pro ($29)
323- **CapCut + ChatGPT:** Manual nhung mien phi — paste transcript, ChatGPT phan tich hooks
324 
325### Distribution 4 nen tang
326 
327| Nen tang | Format | Thoi luong | Caption | Bonus |
328|----------|--------|------------|---------|-------|
329| **TikTok** | 9:16 (1080×1920) | 30-60s | Bold caption tren | Trend audio overlay (volume thap) |
330| **Instagram Reels** | 9:16 | 15-90s | Subtitle dep, font sans-serif | Cover image dep |
331| **YouTube Shorts** | 9:16 | <60s | Auto-caption YouTube | Title chua keyword |
332| **LinkedIn audio** | 1:1 (square video voi audio) | 60-120s | Caption ben duoi | Doc thread bai dai (carousel) |
333 
334**Pro tip:** Moi clip = 1 platform rieng, dung khac caption + cover image. Tang reach.
335 
336---
337 
338## 8. QA audio + Disclosure
339 
340### 5 QA criteria
341 
3421. **Clarity (10 diem):** Giong ro, khong bi ren, khong lap. Test: phat tren loa dien thoai → van nghe ro
3432. **No clipping (10 diem):** Peak khong vuot -1dB. Tool check: Audacity, Adobe Audition, Reaper
3443. **No background noise (10 diem):** Khong tieng quat, xe co, hang xom. Tool: Krisp, NVIDIA Broadcast, Adobe Enhance Speech
3454. **Consistent volume (10 diem):** Loudness on dinh -16 LUFS (podcast) hoac -14 LUFS (TikTok). Tool: Loudness meter trong DAW
3465. **Natural pauses (10 diem):** Pause hop ly, khong robot. Manual review: nghe lai 3 lan
347 
348> **Pass:** 40+/50 diem. <40 = re-render hoac re-record.
349 
350### VN disclosure — khi nao bat buoc
351 
352| Tinh huong | Disclosure | Vi tri |
353|-----------|-----------|--------|
354| Quang cao thuong mai | BAT BUOC | Caption + cuoi audio ("Audio nay su dung voice clone AI") |
355| Podcast personal brand | NEN — minh bach | Episode description |
356| Audiobook fiction | KHONG bat buoc | Optional — credits cuoi |
357| Tin tuc/giao duc | BAT BUOC | Dau audio + caption |
358| Noi dung noi bo cong ty | KHONG bat buoc | n/a |
359 
360**Template disclosure caption:**
361```
362Audio nay su dung cong nghe voice clone AI
363(ElevenLabs / Vbee / [tool ten]). Noi dung do [Ten ban] viet va duyet.
364```
365 
366> **Reference day du:** `references/ai-video-disclosure-vn.md` — Nghi dinh 147/2024,
367> 3 tang disclose, va template cho tung tinh huong (cung ap dung cho audio).
368 
369---
370 
371## 9. Checklist chat luong
372 
373Truoc khi xuat ban audio:
374 
375- [ ] Sample voice clone 3-5 phut, phong yen tinh
376- [ ] Consent form ky ten (neu clone giong nguoi khac)
377- [ ] Use case dung: voiceover (energetic) / podcast (conversational) / audiobook (mid-tempo)
378- [ ] Voice settings phu hop use case (Stability/Similarity/Style)
379- [ ] Loudness chuan: -14 LUFS (TikTok) / -16 LUFS (podcast/audiobook)
380- [ ] Peak khong vuot -1dB (no clipping)
381- [ ] No background noise (Krisp/NVIDIA Broadcast pass)
382- [ ] Pacing dung: 180-220 wpm (TikTok) / 140-160 wpm (podcast) / 150-170 wpm (audiobook)
383- [ ] QA Score 40+/50
384- [ ] Disclosure caption (neu commercial use)
385- [ ] Repurpose plan: 1 podcast → 10 clip distribute 4 platform
386 
View all files on GitHub →

Details

License
MIT
Stars on the repo
★ 599
Checked
Source
minhnv0807/ai-business-skills ↗
Creator
minhnv0807 · 150 listings
View creator

Similar skills

See all →
SkillLong-Form Draftertimscheuerai/content-vault · by timscheueraiDraft written long-form content (newsletter issue, blog post, Substack issue) in your voice. 800-2000 words, structured intro + body + CTA, paragraph-by-paragraph not list-by-list. Pulls voice from /linkedin-copywriter's corpus (same author, same register · longer arc). Runs the brand-doc skill checklist before output. Logs the row in the Notion Content DB and (for newsletters) drafts a separate punchy subject line. Use when asked to "write a newsletter", "draft a blog post", "long-form X", "Substack issue about Y", "weekly newsletter", or "/long-form". For spoken video scripts (YouTube longs / shorts) use /youtube-script instead · the cadence is fundamentally different.★ 37 GitHub starsAgentPodcast Content Analyzerdavila7/claude-code-templates · by davila7Podcast content analysis specialist. Use PROACTIVELY for identifying viral moments, creating chapter markers, extracting SEO keywords, and scoring engagement potential from transcripts.★ 32.3k GitHub starsAgentPodcast Production Editordavila7/claude-code-templates · by davila7Podcast editing and post-production specialist. Use PROACTIVELY for audio editing guidance, show notes creation, chapter markers, timestamp management, and podcast publishing workflows.★ 32.3k GitHub starsAgentPodcast Metadata Specialistdavila7/claude-code-templates · by davila7Podcast metadata and show notes specialist. Use PROACTIVELY for SEO-optimized titles, chapter markers, platform-specific descriptions, and comprehensive publishing metadata.★ 32.3k GitHub starsAgentAudio Transcriberdavila7/claude-code-templates · by davila7Audio transcription specialist. Use PROACTIVELY for extracting accurate transcripts from media files with speaker identification, timestamps, and structured output.★ 32.3k GitHub starsAgentPodcast Trend Scoutdavila7/claude-code-templates · by davila7Podcast trend analysis specialist. Use PROACTIVELY for identifying emerging tech topics, breaking developments, and timely content suggestions for podcast episodes.★ 32.3k GitHub stars

More from minhnv0807

SkillMarketing Plan Builderminhnv0807/ai-business-skills · by minhnv0807Dung khi can ke hoach marketing tong the cho mot ky — muc tieu, phan khuc, kenh, ngan sach, timeline, KPI va ma tran rui ro. Co ca che do ban day du va che do ke hoach 1 trang cho chu doanh nghiep nho. Kich hoat khi user nhac 'lap ke hoach marketing', 'ke hoach MKT', 'marketing plan', 'chien luoc marketing nam', 'plan quy toi', 'ke hoach 1 trang'. Khong dung cho — tinh nguoc ngan sach tu doanh thu thi dung skill 10-tinh-kpi-nguoc; phan bo ngan sach chi tiet theo kenh thi dung skill 61-budget-planning; brief mot chien dich cu the thi dung skill 02-brief-chien-dich.★ 599 GitHub starsSkillOverall Marketing Strategyminhnv0807/ai-business-skills · by minhnv0807Use when the user needs an overall marketing plan for a period — objectives, segments, positioning, channel mix, content direction, budget, timeline, KPIs, and a risk matrix, adapted to US, EU, SEA, or LATAM. Trigger on 'marketing plan', 'marketing strategy for next year', 'go-to-market roadmap', 'plan for Q3', 'we have no marketing plan', 'where should we spend next quarter'. Also use when a founder only says the business needs to grow and has no idea which channel to start with. Not for — one specific campaign, see `02-campaign-brief-global`; working backward from a revenue goal to spend, see `10-reverse-kpi-global`; splitting a budget across channels and months, see `61-budget-planning-global`; taking a brand new product to market, see `59-go-to-market-global`.★ 599 GitHub starsSkillContent Calendar Plannerminhnv0807/ai-business-skills · by minhnv0807Use when the user needs a monthly or weekly content calendar — posting schedule per channel, funnel ratio, content pillars, repurposing matrix, and an owner per slot. Trigger on 'content calendar', 'posting schedule', 'what should we post this month', 'editorial calendar', 'social media plan', 'we post randomly with no plan'. Also use when the user only says the team keeps running out of things to post. Not for — the brief for one specific post, see `36-content-brief-global`; the caption text itself, see `37-social-caption-global`; deciding next period content from last period data, see `40-next-content-plan-global`; a paid campaign timeline, see `02-campaign-brief-global`.★ 599 GitHub starsSkillContent Posting Scheduleminhnv0807/ai-business-skills · by minhnv0807Dung khi can lich dang bai cho ca thang — chot content pillar va ti le, xep bai theo ngay va khung gio, ma tran tai su dung noi dung, va gan muc tieu cho tung tru cot. Kich hoat khi user nhac 'lich noi dung', 'content calendar', 'thang nay dang gi', 'len lich dang bai', 'ke hoach content thang', 'phan bo noi dung'. Khong dung cho — brief tung bai truoc khi viet thi dung skill 36-content-brief; viet caption thanh pham thi dung skill 37-caption-social; lap plan ky sau tu data thi dung skill 40-next-content-plan.★ 599 GitHub starsSkillCampaign Execution Briefminhnv0807/ai-business-skills · by minhnv0807Dung khi can brief mot chien dich cu the cho ca team thuc thi — muc tieu, thong diep, deliverable, timeline phan cong theo tuan, gate duyet va ma tran rui ro. Kich hoat khi user nhac 'brief chien dich', 'ke hoach campaign', 'len brief cho team', 'chien dich thang toi', 'phan cong campaign', 'timeline chien dich'. Khong dung cho — ke hoach marketing ca ky thi dung skill 00-ke-hoach-mkt; danh sach asset can thiet ke thi dung skill 41-campaign-asset-list; giao viec cho tung nguoi thi dung skill 64-team-brief.★ 599 GitHub starsSkillCampaign Brief Frameworkminhnv0807/ai-business-skills · by minhnv0807Use when a specific campaign needs a brief the whole team can execute from — context, objective, audience, core message, creative direction, channels, deliverables, week-by-week timeline, approval gates, and risks. Trigger on 'campaign brief', 'creative brief', 'launch brief', 'brief the team on this campaign', 'we are running a promo next month', 'what is the plan for this campaign'. Also use when the user describes a promotion out loud and asks for something the team can actually run. Not for — the whole period plan, see `00-marketing-plan-global`; the list of design files needed, see `41-campaign-asset-list-global`; assigning work to one person, see `64-team-brief-global`; a new product launch sequence, see `59-go-to-market-global`.★ 599 GitHub stars