Voice and sound
AI voices, music and sound for Foundry VTT
Type one message. Familiar speaks it in the voices you cast, cues the sound, and moves the music with the scene. Your players hear all of it and see the line on the token.
You keep a switch each for voice, mood switching and sound effects: run on its own, wait until asked, or stay quiet. A fourth, Music generation, lets Familiar compose a track of its own, and starts at On request. It all runs in your browser, on provider keys you bring.
What you see and hear
- One message in Claude Code, beside Foundry: the party comes into the tavern out of the rain, Hank walks up to the bar, Marla Tunney and Old Bertram each get a line, and the scene gets its background music and its evening. The clip opens as the first calls land; the 48 seconds of Familiar reading the world before that are cut.
- The door creaks. No effects playlist exists in this world, so a four-second creak is generated, and its card lands in the Foundry chat marked AI Sound.
- Hank's emote posts as a plain chat message, unvoiced, as the message asked.
- The rain is cued first, the world clock moves an hour into the evening, and then Tavern Evening crossfades in, bound to the scene, with the tavern loop from the GM's own soundtrack playlist layered under it. The scene itself is never dimmed.
- The narration, Marla and Old Bertram are spoken in one gapless take, each in their own voice. The lines sit in the chat as one card marked AI Voice, and each line pops up over its speaker's token while it plays.
- Familiar's reply in the terminal lists what played, in order, and says what is still broken: the Character voice key was rejected, so the two NPC lines went through the narrator slot with their own voice ids and still landed under their names.
Hear it
Every clip in these bands is a real take from a live session, recorded with sound, with the ask you read beside it sent word for word. A recorded card plays with sound when you press it, never on its own. How each of these works is in the chapters below, starting with speaking the scene.
Same scene, three switches
One tavern scene, sent twice, each message opening with the switches it sets. First with Speak aloud, Mood switching and Sound effects on Automatic, so one reply posts the exit, plays the creak, speaks the lines and switches the music. Then with all three on On request, and the same reply is text alone.
Library first, then generated
Four asks that show where a sound comes from: your own track when the library has one, a generated clip when it does not, a loop filed as ambience, and a positional sound placed on the map.
One line, four readings
The same line delivered angry, whispering, sung, and with a pause in the middle of it, all in one voice on ElevenLabs eleven_v3, the one model that renders every one of these. Other providers take an emotion hint as an instruction, and none of them sings.
"You should not have come back here."
The scene, spoken as it is written
Familiar voices the lines it writes, in the same reply, one take per turn.
- With Speak aloud on Automatic, the default, the AI voices the scene lines of its own reply: narration in the narrator's voice, each character in theirs, up to twenty lines in one gapless take. Rules answers, prep and lists stay silent.
- Set it to On request and it waits until you ask.
- Two slots. A narrator voice carries description and the beats between people; a character voice carries the people, and a voice pinned to an NPC wins. The AI picks per line.
- In your own chat window, each character's lines carry a chip with their portrait and name, stage directions muted. Click a chip and Familiar speaks that one line in that voice. Speaker chips is on out of the box, in the Chat tab.
- Emotion, a pause before a line, speed and volume are per-provider knobs. Emotion on ElevenLabs needs the eleven_v3 model; speed works everywhere except ElevenLabs; volume is Cartesia only. The table further down says which is which.
- A narration over roughly 280 characters starts speaking at its first sentence boundary while the rest still renders, so a slow voice model gives you the opening line in seconds rather than a long silence. That is Progressive, in the Speech section, on by default while Playback is Immediate.
- Set Playback to Wait for my go and a finished clip holds instead of playing: a note that it is ready, a Play bar in the chat, a pulse on the Familiar button. Press Play, or a key you bind under Configure Controls, or tell your AI to play it, and with broadcast on it starts for you and your players at the same moment, because their copy went ahead while it waited. A held clip expires after ten minutes; Stop drops it; a table chat answer is never held.
- Text over the provider's own cap is split at sentence boundaries and joined into one clip. A line you have heard before comes from the browser cache, for free.
Voice starts switched on, and nothing plays or bills until the Voice tab of the browser that should speak holds a key. Speak aloud is the GM's chat window only; Claude, Codex and the other MCP clients keep calling the voice tools. Automatic spends at most three takes a turn; a fourth is skipped and the reply carries on as text. Progressive applies to Immediate playback after a reply has landed: a voice generated mid-reply, and any held clip, is staged whole. A reply that quotes someone costs one short extra call on your background model, or your chat model without one, to place the chips, unless Speak aloud already split the lines.
Demo clip coming
What the clip will show
- One GM message sets a tavern scene with three speakers.
- The reply lands as text and the voices follow in the same turn: narrator, innkeeper, a second NPC, no gap between the lines. The opening line is already playing while the rest is still rendering.
- The innkeeper's and the second NPC's lines carry their chips in your chat, and the whole take lands in the Foundry chat as one card with a line per speaker.
- Playback switched to Wait for my go for the last message, broadcast on: the Play bar appears, the Familiar button pulses, and Play starts the line for GM and players together.
Cast a voice without opening a catalogue
Describe the character. The AI finds a voice, casts it on the actor, and tells you which one it picked.
- Ask for a gruff older Scotsman and the AI searches the provider's catalogue by gender, language and free text, casts the best match, and names its choice in the reply.
- A Cast chip in the chat carries a Preview button. On ElevenLabs every stock voice has a free sample; on Cartesia about a quarter do; elsewhere a preview is generated on your key, and the tooltip says which before you click.
- Find a voice yourself in the Voice tab: under the slot's model, the Default Voice picker opens on a search box with gender and language filters, a play button beside it auditions the pick, and Add Custom Voice adds one by its id. The same picker serves the narrator slot, the character slot, and Voice Assignments.
- Pin a voice to an actor once and that NPC keeps it every session. An NPC that speaks in table chat without a voice gets one cast on its first spoken reply, and you are whispered which.
- Ask for a different voice model on one take, ElevenLabs v3 for the line that sings, and that take renders on it while the model on your slots stays what it was; the result names the model that spoke.
Labels to search on come from ElevenLabs and Cartesia. OpenAI has thirteen fixed voices, and OpenRouter, NanoGPT and a custom server take a voice name you type. There is no voice picker on the character sheet: casting happens in the chat or in the settings.
Demo clip coming
What the clip will show
- You type: the blacksmith is a gruff older Scotsman, find him a voice.
- A Cast chip appears naming the voice it picked; Preview plays the provider's own sample, free.
- The Voice tab: open the Default Voice picker, filter it to male English voices, and audition one with the play button beside it.
- A second NPC with no voice of its own answers in table chat, gets a voice cast on that first line, and the GM is whispered which one.
Players talk to an NPC in the Foundry chat, and hear it answer
A player types to an NPC in the ordinary Foundry chat. The answer comes back in that NPC's voice.
- A player types @Bram hello in the Foundry chat. Bram answers in his cast voice, spoken from the GM's side, with no tool call and no extra model round. Every NPC a player does not own answers to its name this way out of the box; pin one on its sheet to keep it answering when you switch Any NPC off, in the Chat tab, for a session where a name alone would give something away.
- @familiar reaches the narrator, who answers in the narrator's voice while Speak aloud is on Automatic.
- Mute one NPC from its sheet header, or ask the AI to do it. The AI reads and changes most of Familiar's own settings on request, the sound rows included; a setting that spends your key or reaches the players is the GM's call to widen, and a player's turn can only narrow it.
- A player's own words are never spoken and never become a prompt for a sound. On a player's turn, any tool that changes the world waits for you to confirm.
- Eight seconds between spoken replies from the same NPC. A reply inside that window comes as text.
On request does not silence the table. An NPC in table chat speaks for as long as the Voice tab's own Table chat switch is on, which it is out of the box, and switching it off keeps every table-chat reply as text; only the narrator follows Speak aloud.
What you see and hear
- The GM's Foundry window on the tavern: @bram hello goes into the ordinary Foundry chat under Hank's name, and a card under Bram's name says he is thinking. The nine seconds of waiting are cut.
- Bram's reply lands as a chat card, and a whispered Familiar card tells the GM it is table chat, speaking as Bram, with AI Voice.
- The line plays in Bram's voice while it sits in a bubble over his token behind the bar, marked AI Voice, and the bubble goes when he finishes.
Music and ambience from your own playlists
Say the party pushes into the taproom and Familiar finds the mood in your own playlists, fades over, and binds it to the scene.
- It searches your own Foundry playlists by playlist, folder and track name, with a synonym table that maps tavern, inn and taproom onto the same mood. It never fetches a track: it cues what your world already holds, a loop you asked Familiar to generate, or a track it composed for you.
- A switch crossfades over two seconds and binds the mood to the active scene, so Foundry cues it again on its own next time.
- Mood switching on Automatic, the default, switches when the scene, the location or a fight changes: one switch a minute, one per turn, and a second ask inside that window comes back as skipped. On request waits for you. Off refuses.
- A Stop all audio button sits on the ambience cell, and the classic playlist tools stay: play, stop, fade, create, reorder, volume, one stop for everything.
- Four ways to get audio in. A pack from the Foundry package browser, where Michael Ghelfi Studios ships one whose playlists arrive as compendium packs you drag into the sidebar. Your own files, through Bulk Import on a playlist's configuration sheet. A track from Make music, the next chapter. And services with their own player, which Familiar cannot cue.
Familiar ships no sounds of its own. Syrinscape, Tabletop Audio, Kenku FM, YouTube and Spotify play outside Foundry's player, so the AI will not switch them. An empty world gets a hint that points here.
Demo clip coming
What the clip will show
- You type: we push into the taproom.
- The ambience cell lists the tavern moods it found in your playlists; one fades in, and a chip reads bound to Scene.
- Combat starts and the mood switches by itself; a second switch inside the minute is skipped.
A track composed for the scene, on your own key
Nothing in your playlists fits the crypt? Ask for a slow, menacing bed and Familiar composes one, then waits for you to cue it.
- Up to two minutes of instrumental music from one ask, in the chat or from an MCP client. In Familiar Studio, set the prompt bar to Music, pick thirty seconds, one minute or two, and press Generate: no chat turn, no confirmation, and the card lands in the grid.
- It renders on a key you already hold: the ElevenLabs key on a voice slot, on a paid plan; your fal.ai image key; or a NanoGPT or OpenRouter key in any slot. The Provider row under Music generation picks the route for the chat, MCP clients and the Studio alike, and Automatic takes the first of those that renders music, in that order.
- The track lands in a Familiar Music playlist, set to repeat, with a line that names the provider and describes the track, and gets a player in the chat. It never starts by itself: cue it from the Playlists sidebar or ask for it, and Mood switching finds it by name like any track you own.
- Music generation on the Voice tab starts at On request. On Automatic, Familiar composes a track when the mood changes and nothing in your playlists fits, at most two new ones every half hour. Off stops it composing at all.
- A render is one attempt, never retried: a track is billed for its length, and a second try would bill again.
Always an instrumental, and ElevenLabs refuses a prompt that names a real artist, song or label. NanoGPT, OpenRouter and most fal.ai models report what a track cost, and the Studio card shows it. ElevenLabs reports no price, and neither does the ElevenLabs model fal.ai runs by default. No music model renders a seamless loop, so a track meant to repeat is asked for as an even texture: a bed loops cleanly, a tune with an ending restarts audibly.
Demo clip coming
What the clip will show
- You type: make me a short tavern track for the Rusty Flagon, warm and lively, fiddle and hand drum, about thirty seconds.
- Familiar searches your ambience first and finds nothing, then composes. A Music cell with a player lands in the chat at 0:00, not playing, and the reply says the track is saved to Familiar Music.
- The Playlists sidebar shows Familiar Music with the new track set to repeat, nothing playing.
- The Studio prompt bar switched to Music: thirty seconds, Generate, and a new card with its price, on a route that reports one.
Sound effects: your library first, then generated
The door creaks because the narration said so. If your effects playlist has a creak it plays for free; if not, Familiar generates one.
- A track in your own playlist named Sound Effects, SFX, Effects, One-shots or Stingers plays first, at no cost and with no badge.
- When nothing matches, a one-shot is generated on your ElevenLabs voice key or your fal.ai image key: one to six seconds on Automatic, up to twenty-two on request, with the provider's own price printed on the cell where it reports one.
- Automatic means at most two effects a reply and three generated clips a minute; the next one waits. On request plays only when you ask. Off refuses.
- On another player's turn, Familiar adds a sound only when that player asks for one, and that still asks you; the Solo Player's turns keep automatic sounds.
- Familiar Studio makes one without a chat turn: set the prompt bar to Sound, pick three to twenty-two seconds, press Generate, and the clip lands as a card in the Studio.
- Save keeps a clip as a track in a Familiar Sound Effects playlist. Ask for a rain loop and it is filed in Familiar Ambience, where the music layer finds it. Ask for a waterfall at the cliff and it becomes a positional sound on the map that grows louder as a token walks up.
- Players hear effects through Foundry's own audio while Players hear sound effects is on, the default, and switching it off keeps effects on your own speakers; generated clips are then saved under your world's familiar-sfx folder.
A generated effect bills whichever key you have, so an image key alone is enough to be charged for sound effects, and Sound effects starts on Automatic; set it to On request or Off to hold it. Never music, and loops only when you ask. Effects never duck the music and never wait for a voice line.
What you see and hear
- One message carries three beats: the old side door creaks, thunder rolls overhead, rain starts and keeps going for the rest of the scene.
- Familiar checks the playlists first. The creak and the rain loop are already there, so The Door Creaks plays from Familiar Sound Effects with nothing generated.
- Thunder has no track, so a five-second rumble is generated on ElevenLabs, an AI Sound card appears in Foundry, and the clip is saved in Familiar Sound Effects as Thunder Rolls Overhead.
- Rain Loop from Familiar Ambience starts on repeat and runs until you stop it.
The other direction: the table, written down
Switch on transcription. The session is written down as it is spoken, into a journal you can search. Next week the AI reads it back to you.
- Your microphone streams to Gladia, Deepgram or AssemblyAI on your key, and the words land in a panel in the chat window. The audio itself is never stored, only the text.
- Deepgram and AssemblyAI label the speakers. Rename Speaker 0 to Ben once and every line, past and future, follows, across sessions.
- Search the transcript with Ctrl+F, drop a bookmark with F9, export in five formats including SRT. The journal fills every thirty seconds.
- After the session, three settings: the transcript becomes searchable for the AI (on by default), so what did we decide about the duke gets an answer next week; a recap page written on your chat model (opt-in); and players read along live in a read-only panel (opt-in).
- The microphone sits in the chat box whatever the settings say. With no speech to text key it is dimmed and a click opens the Transcription tab on the key field; with a key, one click turns Dictation on and starts listening, and the arrow beside it sets how dictated text is sent or turns Live transcription on. Ctrl+Shift+D is push-to-talk once Dictation is on; hands-free lets a pause send.
Gladia, the default, does not tell speakers apart live. The microphone needs a secure page: https, or Foundry opened on localhost. One key does not cover both speech and voices; transcription has its own tab and its own key.
Demo clip coming
What the clip will show
- The mic is on; two people speak and the lines arrive with speaker labels.
- Speaker 0 is renamed to Ben (DM) and every line updates; F9 drops a bookmark into the journal.
- Stop: a Summary page appears in the journal. Next session, the chat is asked what was decided about the duke, and quotes the transcript.
Your key, your cost
Your licence pays for Familiar: the tools, the rules engine, every update. It never pays for a second of audio. Voices, sound effects, music and transcription run on keys you make at the providers of your choice and paste into the Voice, Image and Transcription tabs; each provider bills you at its own price, and Familiar adds nothing on top.
Three things Familiar never does: meter your audio, mark up your provider, or hide the price. Where a provider reports what a clip cost, the module prints it on the cell. Where it reports nothing, Familiar shows nothing rather than guessing.
Spending is held down before anything is billed. A repeated line plays from the browser cache. A sound effect is looked up in your own playlists before one is generated, and an automatic one-shot is capped at six seconds and three generated clips a minute. Searching and casting voices cost nothing; on ElevenLabs a preview is the provider's own free sample. Before it pays for a sound effect or a track, Familiar asks Foundry whether it will save the file, so a refused upload bills nothing. An effect that fails to save after billing stays in the page until you reload, and the same ask saves it at no new charge.
One key, several jobs. An ElevenLabs voice key also generates sound effects and, on a paid plan, music. A fal.ai image key makes images, sound effects, music and short video clips; the Make music chapter lists the other keys that compose. That cuts both ways: an image key alone is a sound-effect key, and the sound-effects chapter says how to hold it; Music generation and Video generation start at On request, so neither bills until you ask. Transcription and dictation share a key of their own. Keys stay in your Foundry client settings, in your browser; audio is made browser-direct, and no Familiar server sits in the audio path.
A few list prices, quoted with their source so you can recompute them:
- ElevenLabs text to speech1 credit per character on the standard models; the Creator plan is $22 a month for 121,000 creditsA sixty-character line is about sixty credits, so the Creator plan covers roughly two thousand such lines a month. Source
- Cartesia Sonic text to speech$5 a month for 100,000 credits on the Pro plan, about 133 minutes of speech; the free plan holds 20,000 creditsThe free plan is about 27 minutes of speech a month; Pro is about two hours. Source
- OpenAI tts-1 and tts-1-hd$15 and $30 per million charactersFifteen thousand characters of speech, a long session, is about 23 cents on tts-1 and 45 on tts-1-hd. Source
- OpenRouter hexgrad/kokoro-82m$0.62 per million charactersThe same fifteen thousand characters are about one cent. Source
- fal.ai ElevenLabs Sound Effects v2$0.002 per second of generated audioA three-second creak is about six tenths of a cent; a twenty-second loop is four cents. Source
- Deepgram Nova-3 streaming$0.0048 per minute at the current pay-as-you-go rate; the regular rate is $0.0077; a new account starts with $200 of creditA four-hour session is about $1.15 at the current rate and $1.85 at the regular one. Source
- Gladia real-time transcription$0.75 per hour on the Starter plan; a new account starts with €50 of creditA four-hour session is $3 on Starter; Gladia advertises its own starting credit as about sixty hours of real time. Source
- AssemblyAI streaming transcription$0.15 per hour on Universal-Streaming, $0.45 on Universal-3 Pro; a new account starts with $50 of creditA four-hour session is 60 cents, or $1.80 on the Pro model; the clock runs while the connection is open, idle time included. Source
Prices checked on 3 October 2026 on the providers' public pricing pages.
Providers and settings
Speech runs on the provider you bring, and what a line can do follows that choice: Familiar sends only the knobs a provider understands and logs the ones it skips. Transcription has its own three providers, with their own key.
Speech, by provider:
| Provider | Default model | Emotion hint | Pause before a line | Speed | Volume | Language per line | Voice catalogue and preview |
|---|---|---|---|---|---|---|---|
| ElevenLabs | eleven_flash_v2_5 | On eleven_v3 only, which also sings (experimental, and it varies by voice) | Yes | No | No | Yes | Full catalogue with labels; a free sample on every stock voice |
| Cartesia | sonic-3.5 | Yes, English, from a fixed list | Yes | 0.6 to 1.5 | 0.5 to 2 | Yes, with locale | Full catalogue with labels; a sample on about a quarter of the voices |
| OpenAI TTS | gpt-4o-mini-tts | Yes, as an instruction | No, and the reply says so | 0.25 to 4 | No | No | Thirteen fixed voices; a preview is generated |
| OpenRouter TTS | hexgrad/kokoro-82m | On OpenAI models only | No | Yes | No | No | Type a voice name; a preview is generated |
| NanoGPT TTS | Kokoro-82m | Yes, as an instruction | No | Yes | No | No | Type a voice name; billed from your NanoGPT balance; a preview is generated |
| Custom OpenAI-compatible | the model you name | Yes, as an instruction | No | Yes | No | No | Type a voice name; a preview is generated |
Transcription, by provider:
| Provider | Model | Speaker labels | Languages | To start |
|---|---|---|---|---|
| Gladia | Solaria-1, the default | No | Detected automatically, switches mid-sentence | €50 of credit |
| Deepgram | Nova-3 | Yes, numbered | Many | $200 of credit |
| AssemblyAI | Universal-3 Pro streaming | Yes, lettered | English, Spanish, German, French, Portuguese, Italian | $50 of credit |
- Voice starts switched on, per browser, and stays silent and unbilled until that browser holds a key. The Voice tab holds the switch, the narrator and character slots with their providers, keys, models and searchable voice pickers, Voice Assignments, and the Speech section: Speak aloud, Playback, Chat log, Table chat, Cast voices, Speech bubbles, Voice volume, Progressive, and the two dip rows, Music under voice and Ambient sounds.
- Player Broadcast, Ambience, Sound effects and Music generation sit in the same tab. Broadcast is one select: Off, Manual or Automatic. Mood switching (under Ambience), Sound effects and Music generation each take Off, On request or Automatic. All four are world settings. Broadcast, Mood switching and Sound effects default to Automatic, so out of the box your players hear what Familiar makes and a generated effect bills the key you pasted; each select's Off and On request rows hold it. Music generation starts at On request, with a Provider row under it (Automatic, ElevenLabs, fal.ai, NanoGPT or OpenRouter). With Voice off, the tab's rows stay, greyed. The two dip rows are each listener's own and also appear in Foundry's Module Settings, where a player sets theirs.
- Transcription has its own tab, in three sections. Speech to Text holds Live transcription and Dictation, with its send mode and pause; Speech to Text Provider holds the provider, key and model the two share; After the Session holds searchable by the AI (on), a recap page (off) and players read along (off).
- Keys are stored in your Foundry client settings, in your browser, and never pass through a Familiar server.
- Keyboard: Stop All Familiar Audio is unbound until you bind it, F9 bookmarks the transcript, Ctrl+F searches the panel, Ctrl+Shift+D is push-to-talk dictation. The Stop button also answers your keyboard's media keys.
- Over MCP the same tools run, and the clip plays in the Foundry tab, never in the client.
Works in Foundry v13 and v14, verified with v14.368. Model choice for the chat side lives in the model guide; the tool catalogue lives on the capabilities page.
Questions before you switch sound on
Does Familiar make music?
Yes, when you ask. Familiar composes an instrumental track, files it in a Familiar Music playlist and never plays it until you cue it. Your own playlists still come first: a pack from the Foundry package browser, your own files through Bulk Import, or an adventure module's playlists. Make music has the keys, the switch and the caps; music and ambience says how a mood is found and bound to the scene.
Does it copy my voice, or anyone else's?
No. Familiar has no voice copying and no speech-to-speech mode, on purpose: the legal ground under a copied voice is thin, and a table does not need it. Voices come from a provider's catalogue, or from a voice id you paste for a voice you already own at that provider.
Do my players need a key, or a module?
Neither. Voice clips and sound effects reach them through Foundry's own audio, under their own interface volume. The spoken line shows in a bubble on the token and lands in their chat under the speaker's name, and their music dips under a voice and swells back. Broadcast is Automatic out of the box; Manual puts a button on each clip so you choose, Off keeps voice on your speakers. They install nothing and pay nothing.
What appears in my world?
Three playlists once a clip or a track is filed: Familiar Ambience, Familiar Sound Effects and Familiar Music. Three folders under the world's data, familiar-tts for broadcast clips, familiar-sfx for effects and familiar-music for tracks, one file per unique clip. One Familiar journal folder, with Art, Transcripts and Sessions inside it, once Familiar writes a page. And a voice flag on each actor you cast. Nothing leaves the world, and nothing is uploaded anywhere but your own Foundry server.
Does it delete old clips?
No. Foundry gives a module no way to delete a file, so Familiar keeps no timer that would pretend otherwise, for familiar-tts, familiar-sfx and familiar-music alike. Clips are named by their content, so the same line in the same voice reuses its file; the folders only grow, so prune them by hand.
Why does my player hear nothing?
Browsers block audio until the page has been clicked or a key pressed, and Foundry reports that lock. One click or keypress in the Foundry window lifts it, and the next clip plays. Still silent? Check that Player Broadcast is not Off, and that the player's interface volume in Foundry is up.
Does it work on Forge, or over plain http?
Voices, ambience and effects work anywhere Foundry runs. Two things need a secure page, https or Foundry opened on localhost on the machine that runs it: the microphone for transcription and dictation, and the browser cache that makes a repeated line free. On plain http the line is generated again instead.
Does it work from Claude Desktop, or another MCP client?
Yes, with the same tools, and the audio plays in the Foundry tab rather than in the client. Three things to know. Claude Desktop's curated tool set leaves the voice bundle out, so add FAMILIAR_TOOL_BUNDLES=voice-generation to its config. Speak aloud, Mood switching, Sound effects and Music generation are read from get-world-info, so an MCP client follows the same switches the built-in chat does. And with Playback on Wait for my go, an MCP client's result comes back with the narration held and a holdId, which play-held-voice and discard-held-voice act on; the chat card appears at your Play, not before.
Which voice provider should I start with?
ElevenLabs has the widest catalogue and a free sample on every stock voice. Cartesia and OpenAI both take an emotion hint on any voice, Cartesia in English, OpenAI as an instruction; OpenAI bills per character while Cartesia runs on monthly credits with a free tier. OpenRouter reaches Kokoro on a key you may already use for chat, and NanoGPT bills speech against the same balance as its chat models. The table above says what each one can do, and the dated prices say what a session costs.
Try it at your next session
$6 per month or $48 per year after two weeks free, or $99 once for life. Your voice, music, sound and transcription providers bill separately, at their own prices. Everything else Familiar does at the table is on the capabilities page.