> ## Documentation Index > Fetch the complete documentation index at: https://docs.decktalk.ai/llms.txt > Use this file to discover all available pages before exploring further. # Write a dialogue > Give a section to two voices, a narrator and a guest, with one line before each turn, and build it on placeholders before buying a take. A film may be read by more than one voice. Each voice is a table of `decktalk.toml`, and a line holding only `[voice NAME]` in `script.md` hands what follows to that voice. A section that names no voice is read by the default voice whole, exactly as a one-voice film is. `decktalk init --example interview my-interview` writes a project whose second section is a dialogue between a narrator and a guest, both ElevenLabs voices with their ids left empty, so it builds on placeholders until you name them. ## Declare the voices Write one `[voices.NAME]` table per voice, and name the default voice in `[narration] voice`. A voice name is a lower-case letter followed by lower-case letters and digits. ```toml decktalk.toml theme={null} [narration] voice = "narrator" # the default voice, which reads every section no [voice NAME] line names [voices.narrator] provider = "elevenlabs" id = "" [voices.guest] provider = "elevenlabs" id = "" speed = 1.05 # this voice's own pace stability = 0.4 # over [elevenlabs] stability, for this voice alone ``` Once one voice table is written, every voice needs its own, the default included. A voice may set any voice setting of its provider's table for itself, and the two voices may sit on different providers. A voice id may also come from the environment as `DECKTALK_VOICES__ID`, such as `DECKTALK_VOICES_GUEST_ID`. ## Hand the turns to them In the section that is a dialogue, open every turn with a voice direction, the first included. ```markdown script.md theme={null} ## 2. The interview [voice narrator] How do you write a film one sentence at a time? [voice guest] I write the sentence first. [beat] Then the picture waits for it. [pause 1] [voice narrator] And when the sentence changes? [voice guest] Only that part is made again. ``` Each stretch one voice reads is a **turn**, and each turn is voiced as its own take, so changing the guest's last sentence voices that turn alone. Where the voice changes, the turns are joined across `[narration] turn_gap_seconds`, `0.3` seconds by default, and a `[pause N]` written there wins, as the one second above does. The next section starts with the default voice again. Turns are counted from one within their section, so the guest's last turn above is turn 4 of section 2. A take you do not like is bought again on its own with `decktalk narrate --turn 2.4 --spend`, which keeps every other turn's take and sets the one it replaces aside, as [Voice one turn again](/guides/rebuild-one-section#voice-one-turn-again) describes. A cue phrase in `cues.json` may sit in any turn of its section, because a section's words run on one clock. The transcript names the voice before each turn of a section spoken in more than one voice, so a reader who cannot hear the film knows who says each line. The captions carry the words alone unless you turn on `[output] caption_voices`, which names the voice of every caption of a dialogue: `` in the `.vtt`, and `guest: ` before the line in the `.srt`. ```toml theme={null} [output] caption_voices = true ``` The page knows who says each word whatever you choose: every item of `DeckTalk.words` carries its `voice` and its `turn`, and in the captioned copy that `[output] captioned` writes, every caption carries them as `data-voice` and `data-turn`. The interview example sets the guest's captions on the right that way, under the guest's bubbles, and no caption it draws names a voice. [Accessible video](/guides/accessible-video#a-captioned-copy-for-a-place-that-cannot-load-a-caption-file) has the whole of the captioned copy. ## Check it before you build `decktalk check --no-pages` reads the directions against the voices you declared, and says how much each voice reads and what it costs. * [`SCRIPT_VOICE_UNKNOWN`](/reference/findings/SCRIPT_VOICE_UNKNOWN): a direction names no declared voice, with the nearest name. * [`SCRIPT_VOICE_UNMARKED`](/reference/findings/SCRIPT_VOICE_UNMARKED): a section that names a voice has a turn no direction opens. * [`SCRIPT_VOICE_BARE`](/reference/findings/SCRIPT_VOICE_BARE): a line holding only a note such as `[guest]` is exactly a voice's name, so it plays as a beat. Write `[voice guest]`. The same note inside a paragraph is [`SCRIPT_UNFINISHED`](/reference/findings/SCRIPT_UNFINISHED). * [`VOICE_UNUSED`](/reference/findings/VOICE_UNUSED): a declared voice reads no turn. `decktalk status` names the voices of every section, `decktalk --json status` carries the take state of every turn under each section's `turns`, and once `decktalk narrate` has run, `decktalk words` heads each turn's words with its voice. ## Build it `decktalk build --no-spend` plays a placeholder for every turn with no voiced take, so the pacing and the cues are real before anything is bought. A voice with no id cannot be bought: `--no-spend` plays its placeholders and the `TAKE_MISSING` finding of each of its turns names the `[voices.NAME] id` to set, and `--spend` stops at `narrate` with an [`INPUT`](/reference/errors/INPUT) error naming the voice, before anything is bought. With both ids set and the key in `.env`, `decktalk build --spend` buys every turn's take. A voiced take that holds no sound plays its turn as silence and is reported as [`TAKE_SILENT`](/reference/findings/TAKE_SILENT), a warning that names the turn, so `decktalk narrate --turn N.T --spend` buys that turn again. ## Related * [script.md](/reference/script-md#voice-directions-and-turns) for every rule a voice direction follows. * [decktalk.toml](/reference/decktalk-toml) for the voice tables and their keys. * [Rebuild one section](/guides/rebuild-one-section) for what each change voices again. This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.