菜单
Generate speech audio using Gemini TTS. Use when user asks for "text to speech", "voiceover", "narration", "voice", "audio", "podcast", "dialogue", "read this", "speak this", or any speech synthesis request.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | tts-content |
| description | Generate speech audio using Gemini TTS. Use when user asks for "text to speech", "voiceover", "narration", "voice", "audio", "podcast", "dialogue", "read this", "speak this", or any speech synthesis request. |
| license | MIT |
| allowed-tools | ["generateVoiceover","generateMultiSpeakerVoiceover"] |
Ask the user:
What type of audio do you need?
- Single Narrator - One voice reading text
- Multi-Speaker - Dialogue, podcast, conversation
- Voiceover - For video/presentation
- Character Voice - Specific personality/style
Store answer as: audioType
What voice characteristics do you want?
Gender:
- Female voice
- Male voice
Tone:
- Professional/Authoritative
- Friendly/Warm
- Energetic/Excited
- Calm/Soothing
- Casual/Conversational
How many speakers do you need? (2-4)
For each speaker, I'll ask about their voice.
| Voice | Characteristics | Best For |
|---|---|---|
| Zephyr | Warm, friendly, versatile | General narration |
| Aoede | Bright, energetic | Excited content |
| Kore | Calm, soothing | Meditation, ASMR |
| Leda | Professional, clear | Corporate, tutorials |
| Achernar | Authoritative | News, announcements |
| Pulcherrima | Elegant, refined | Luxury, premium |
| Voice | Characteristics | Best For |
|---|---|---|
| Puck | Friendly, casual | Casual content |
| Charon | Deep, authoritative | Documentary |
| Orus | Warm, trustworthy | Explainers |
| Fenrir | Energetic, dynamic | Ads, promos |
| Schedar | Professional, clear | Corporate |
| Achird | Calm, measured | Tutorials |
| Content Type | Recommended Voices |
|---|---|
| Tutorial/Explainer | Leda, Achird, Orus |
| Podcast | Zephyr + Puck (duo) |
| Advertisement | Fenrir, Aoede |
| Meditation/Calm | Kore, Charon |
| Corporate | Achernar, Schedar |
| Storytelling | Zephyr, Orus |
Ask the user:
How should the voice sound?
Style:
neutral- Standard deliveryvocal_smile- Bright, sunnynewscaster- Professional newswhisper- Soft, intimateexcited- High energycasual- Relaxed, informalserious- Grave, formalPace:
natural- Normal speedslow- Deliberate, measuredenergetic- Quick, upbeatrapid_fire- Very fastAccent (optional):
american_general- Standard USbritish_rp- British received pronunciationaustralian- Australian accent
Store answers as: style, pace, accent
Format the text with speaker labels:
Host: Welcome to the show!
Guest: Thanks for having me!
Host: So tell us about your project.
Guest: Well, it started when...
User can add inline tags for expression:
[excited] This is amazing!
[whispers] But keep it a secret.
[laughs] That's hilarious!
[sighs] It's been a long day.
[slow] Listen carefully now.
Available Tags:
[excited], [whispers], [laughs], [sighs], [gasp],
[sarcastic], [serious], [slow], [fast], [short pause], [long pause]
Show summary:
📋 TTS GENERATION PLAN
======================
Type: {audioType}
Voice(s): {voiceNames}
Style: {style}
Pace: {pace}
Text length: {wordCount} words
Estimated Cost: ~${cost}
Proceed? (yes/no)
Use the pre-built workflow function — it validates, retries, saves the .wav, and reports cost:
import { generateVoiceover } from '../index';
const result = await generateVoiceover({
script: text,
outputPath: 'output.wav',
voiceName,
voiceStyle: { style, pace, accent }
});
// result.data.audioPath, result.data.cost.totalCost
import { generateMultiSpeakerVoiceover } from '../index';
const result = await generateMultiSpeakerVoiceover({
script: dialogueText,
speakers: [
{ speaker: 'Host', voiceName: 'Zephyr', voiceStyle: { style: 'vocal_smile' } },
{ speaker: 'Guest', voiceName: 'Puck', voiceStyle: { style: 'casual' } }
],
outputPath: 'podcast.wav'
});
speakers:
- name: Host
voice: Zephyr
style: vocal_smile
pace: natural
- name: Guest
voice: Puck
style: casual
pace: natural
voice: Leda
style: neutral
pace: slow
accent: american_general
voice: Fenrir
style: promo_hype
pace: energetic
voice: Kore
style: whisper
pace: slow
# Or use custom audioProfile:
audioProfile: "Calm, soothing meditation guide with gentle pauses"
Achernar, Aoede, Autonoe, Callirrhoe, Despina, Erinome, Gacrux, Kore, Laomedeia, Leda, Pulcherrima, Sulafat, Vindemiatrix, Zephyr
Achird, Algenib, Algieba, Alnilam, Charon, Enceladus, Fenrir, Iapetus, Orus, Puck, Rasalgethi, Sadachbia, Sadaltager, Schedar, Umbriel, Zubenelgenubi
| Model | Input | Audio Output |
|---|---|---|
| gemini-2.5-flash-tts | $0.50/M tokens | $12.00/M tokens |
| gemini-3.1-flash-tts | $0.75/M tokens | $12.00/M tokens |
Estimate: ~$0.001 per sentence, ~$0.02 per paragraph
MANDATORY pre-flight check that runs BEFORE any content plan or generation. Classifies the topic, verifies project/brand/product context, resolves the required reusable assets (characters, products, logos, voices) from the asset registry, and provides/generates whatever is missing — saving paths for reuse. Use whenever the user asks to plan a campaign, make a marketing plan, or create/generate any image, video, voiceover, or music.
Generate music using Gemini Lyria. Use for background music, jingles, intros, soundtracks, and complete songs WITH sung vocals — Lyria 3 sings your exact lyrics (8 languages, rap/sung delivery).
Generate images using Gemini 3 Image (Nano Banana). Use for thumbnails, carousels, infographics, social graphics, product photos.
Generate video content using Gemini Veo. Use when user asks to create video, TikTok ad, Instagram Reel, YouTube video, product video, explainer.
Generate voiceover audio using Gemini TTS. Use for narration, voiceovers, podcasts, multi-speaker dialogue.
Write the words — scroll-stopping hooks, framework-driven scripts, and platform-ready captions with hashtags. Use when the user needs hook ideas, a video/ad script, ad copy, post captions, or says "what should I post", "write a script", "give me hooks", "write the caption".