# Dialogue And Voice > Use when a generated clip needs someone to speak, when a clip came back with invented speech in the wrong language, when lip-sync cuts off mid-line, when unwanted text renders on screen, or when the audio mix sounds cluttered. The dialogue, voice-profile and audio-layer rules - including the quotation-mark question and the ellipsis bug that silently kills lip-sync. - Skill: `raphaelbgr/dialogue-and-voice` (Agent Skill) - Install (CLI): `npx skillmds@latest add raphaelbgr/dialogue-and-voice` - Raw SKILL.md: https://api.skillmd.com/api/skills/raphaelbgr/dialogue-and-voice/raw - Safety review: pending - Works with: Claude Code, Claude.ai, OpenAI Codex - Category: Coding & Dev Tools - Author: raphaelbgr (https://skillmd.com/u/raphaelbgr) - Updated: 2026-09-17 - Page: https://skillmd.com/skills/raphaelbgr/dialogue-and-voice --- # Dialogue, voice and audio Audio is generated whether you direct it or not. Leaving it blank is the single most common mistake: the model invents speech, usually in English, and burns the clip. --- ## 1. The audio hierarchy Direct these four, in this order of priority: 1. **Dialogue** — foreground, most important 2. **SFX** — tied to a visible action 3. **Ambience** — the background bed 4. **Music** — **add in post-production only** (see §6) --- ## 2. Dialogue format ``` Dialogue in : speaks in . He/She says: Voice: , years old, , , , . ``` **Three rules that each cost a generation to learn:** ### Quotation marks — the contested one > `[CONTESTED]` Google's Veo prompt guide shows attributed dialogue **with** quotation > marks (*A woman says, "We have to leave now."*). Separate Google guidance says to use > **a colon after the speaker's action and avoid quotation marks**, because quotes push > the model toward rendering the text visually in the video. > > **Field testing sided with the no-quotes form**, and it composes with the known caption > bug — anything that nudges the model toward rendering text makes burned-in subtitles > more likely. **Default to the colon form.** If speech fails to trigger at all, try the > quoted form as a fallback and note which one your footage came from. ``` Prefer: Man says: Bom dia! Fallback: A woman says, "We have to leave now." ``` ### No ellipsis, no mid-sentence periods An `...` or a full stop in the middle of a line **stops the voice and the lip-sync dead.** Replace mid-sentence periods with commas; use a period or question mark only at the very end. For genuinely separate thoughts, split into two attributed statements. ``` Wrong: She says: I want to get so full that... what is it called? Wrong: She says: And the next day, I wake up wrecked. That is what I want. Right: She says: And the next day I wake up wrecked, cooked like an old puppet, that is what I want, and you? Right: He says in Brazilian Portuguese: Eu vou querer tangerina. He says in Brazilian Portuguese: Só não tá gelada, tá? ``` ### Always name the language Omitting the language causes audio-generation failures and random-language output. Every spoken line — and every background murmur — states its language. ``` Wrong: She says: Hm, abacaxi. Right: She speaks in Brazilian Portuguese with deadpan delivery. She says: Hm, abacaxi. ``` Non-English dialogue **keeps its accents** — `nao → não`, `e → é`. Accents drive pronunciation; never ASCII-strip a dialogue line. Spell numbers out in words. --- ## 3. Line length and lip-sync | Type | Max words | Notes | |---|---|---| | Short reaction | 2–4 | Best lip-sync | | Normal line | 5–7 | Good lip-sync | | Long line | 8–10 | Acceptable | | Too long | 10+ | Split across clips | One or two short attributed lines per clip. Crowding garbles the lip-sync and the mix. **Do not write "precise lip sync"** and expect it — exact word-level sync is documented as unreliable across model families. Ask for the line, accept the approximation, or dub in post. --- ## 4. Voice profiles Define one per speaking character, and reuse it verbatim: | Attribute | Example | |---|---| | Gender | Male / Female | | Age | 25–28 years old | | Language | Brazilian Portuguese | | Energy | Low / Medium / High | | Style | Deadpan / Warm / Excited / Casual | | Delivery | Monotone / Animated / Natural | | Emotional quality | Sleepy / Friendly / Understated / Eager | ``` Voice: Male, 25-28 years old, deadpan monotone Brazilian Portuguese, casual understated delivery, low energy, sounds like he just woke up, zero emotional reaction. Voice: Male, 40-45 years old, warm friendly Brazilian Portuguese, relaxed casual delivery, medium energy, slight smile in the voice, genuine helpfulness. ``` Naming the speaker in every line prevents voice drift between clips. --- ## 5. Ambience — concrete audible sounds only Use **3–5 concrete sounds**. Specify the language of any voices. Be specific: "keyboard clacking", not "office sounds". ``` Wrong: Ambience: city sounds, people talking, background noise Right: Ambience: car engine hum, a single motorcycle passing, muffled conversation in Brazilian Portuguese, footsteps on concrete ``` **What is not an ambient sound** — this is where prompts quietly rot: | Do not write | Why | Write instead | |---|---|---| | "earrings swaying" | motion is visual, not audible | "earrings jingling softly" | | "dramatic pause" | silence is the absence of sound | "a clock ticking quietly" | | "confident energy" | abstract, not audible | (delete — that is the dialogue's job) | | "animated gesture sounds" | not specific | "fabric rustling from gestures" | | "intimate atmosphere" | abstract | "soft room tone" | Reliable concrete beds: soft room tone · clock ticking quietly · distant traffic hum · fabric rustling · silverware clinking · a glass setting down · a gentle exhale · air circulation · a chair creaking. **One bed per clip.** Layering muddies the mix. --- ## 6. SFX and music **SFX: exactly one per clip**, tied to a visible action. ``` SFX: door handle click as the door opens SFX: two hollow knocks on the wooden door SFX: None. ``` Write sound events as **verbs**, not nouns — *"the mask tearing free with a sharp rip of fabric"*, not *"fabric, ripping"*. Where a model exposes named layers, use all three: ``` Audio. Foreground: . Bed: . Background: . ``` **Music: None. — always.** The model generates a *different* track for every clip, and the assembly sounds disjointed. Lay one track across the whole timeline in post, ducked −8 dB to −12 dB under dialogue. --- ## 7. Silence Speech cues are the primary trigger for **both** unwanted audio and burned-in captions. To get a genuinely silent clip: - Remove every quoted line and every speech cue. - **Never mention the mouth, lips or speaking** — "his mouth opens slightly as if about to speak" and "lips press together" both generate actual speech. Convey emotion through eyebrows, jaw and eyes only. - State the silence positively and explicitly: `Dialogue: None. He does NOT speak. Mouth closed. Silent scene.` plus `No dialogue. No music. Ambient room tone only.` - A thin ambient bed is safer than total dead air, which can read as a glitch. - **Never add an `Audio language:` line to a silent clip** — it forces speech. - In Google Flow there is also an explicit toggle: View Settings → *Return silent videos: On*. --- ## 8. Failure modes worth knowing - **Depicting people under 18 has been observed to kill audio entirely** ("audio generation failed"). Age the character up, or accept a silent clip. - **Upscaling 720p → 1080p strips the audio.** Plan the resolution before you commit. - **Re-voicing a clip's spoken audio is restricted** on Omni Flash — you cannot reliably chat-edit speech after the fact. More hard-won failures: [`docs/veo3-field-lessons.md`](../../docs/veo3-field-lessons.md).