Chasca
Get started
Docs / Voices

Reference

Voices

Sulafat narrates by default. Pick any of the 30 narrators and it speaks every supported language in the same voice, with the emotion your script calls for.

Narrators

Every narrator speaks every narration language, so a course keeps one consistent voice from English to Hindi to Japanese. They perform rather than read: each scene gets its own tone, and inline audio tags add a whisper, a laugh or a pause exactly where the script asks for one. Ids look like chasca:sulafat, the default.

Warm and friendly

  • Sulafat Warm Default

    Warm and natural, like a favorite teacher. The all-purpose default.

    chasca:sulafat

  • Achird Friendly

    Friendly and approachable, like a helpful colleague.

    chasca:achird

  • Callirrhoe Easy-going

    Easy-going and relaxed. Makes hard ideas feel light.

    chasca:callirrhoe

  • Umbriel Easy-going

    Laid-back and conversational, never in a hurry.

    chasca:umbriel

  • Zubenelgenubi Casual

    Casual and down to earth, like a podcast host.

    chasca:zubenelgenubi

  • Vindemiatrix Gentle

    Gentle and patient. Good for sensitive or reflective topics.

    chasca:vindemiatrix

Clear and informative

  • Charon Informative

    Informative and assured, like a documentary narrator.

    chasca:charon

  • Rasalgethi Informative

    Measured and informative, with quiet authority.

    chasca:rasalgethi

  • Sadaltager Knowledgeable

    Knowledgeable and curious, like a favorite professor.

    chasca:sadaltager

  • Iapetus Clear

    Clear and steady. Every word lands.

    chasca:iapetus

  • Erinome Clear

    Crisp and clear. Ideal for step-by-step walkthroughs.

    chasca:erinome

  • Schedar Even

    Even and balanced. Neutral narration for any topic.

    chasca:schedar

Bright and upbeat

  • Zephyr Bright

    Bright and cheerful, with energy that keeps things moving.

    chasca:zephyr

  • Autonoe Bright

    Bright and articulate. Lively without being loud.

    chasca:autonoe

  • Puck Upbeat

    Upbeat and playful. Great for hooks and social clips.

    chasca:puck

  • Laomedeia Upbeat

    Upbeat and encouraging, with real momentum.

    chasca:laomedeia

  • Sadachbia Lively

    Lively and expressive. High energy for dynamic topics.

    chasca:sadachbia

  • Fenrir Excitable

    Excitable and animated. Made for surprising facts.

    chasca:fenrir

  • Leda Youthful

    Youthful and playful. A good fit for younger audiences.

    chasca:leda

Smooth and polished

  • Algieba Smooth

    Smooth and polished. Premium brand narration.

    chasca:algieba

  • Despina Smooth

    Smooth and flowing narration that feels effortless.

    chasca:despina

  • Aoede Breezy

    Breezy and light, like an easy conversation.

    chasca:aoede

  • Pulcherrima Forward

    Forward and engaging. Holds attention from the first line.

    chasca:pulcherrima

Firm and confident

  • Kore Firm

    Firm and confident. Clear guidance with conviction.

    chasca:kore

  • Orus Firm

    Firm and grounded. Steady, trustworthy narration.

    chasca:orus

  • Alnilam Firm

    Firm and direct. Straight to the point.

    chasca:alnilam

Soft and textured

  • Achernar Soft

    Soft and calm. Soothing for reflective topics.

    chasca:achernar

  • Enceladus Breathy

    Breathy and intimate, like a late-night storyteller.

    chasca:enceladus

  • Gacrux Mature

    Mature and wise. Warm authority for serious subjects.

    chasca:gacrux

  • Algenib Gravelly

    Gravelly and characterful. Stands out in a feed.

    chasca:algenib

For younger audiences, Leda sounds like an older kid explaining to younger ones, and pairs well with the Crayon drawing style.

Directing the narrator

Chasca writes the direction for you: a voice style for the whole video, a short delivery note per scene, and a few audio tags where the voice should change. When you send your own scene graph you can write them yourself.

  • voiceStyle: who the narrator is for this video and how they feel about the topic.
  • delivery (per scene): the emotional beat, like “hushed intrigue building to surprise”.
  • Audio tags in the narration, in square brackets: emotions such as [curious], [excited] or [warmly], delivery such as [whispers] or [slowly], reactions such as [laughs] or [sighs], and pauses ([short pause], [long pause]). Tags are performed, never spoken, drawn or captioned. Write them in English in any language.
JSON 
{
  "voiceStyle": "A delighted science teacher sharing a favorite everyday mystery.",
  "scenes": [{
    "delivery": "curious wonder building to a reveal",
    "narration": "[curious] Sunlight looks white, but it carries every color… [amazed] so blue reaches your eye from every direction."
  }]
}

Discovering voices

The catalog can grow, so don’t hard-code lists: ask the API. GET /v1/voices needs no key, and every entry includes its tone, its group and a preview_url you can play.

Terminal 
# every narrator, each with a preview you can play
curl "https://app.trychasca.com/api/v1/voices"

Then pass the id as voice when you create a video:

Terminal 
curl -X POST https://app.trychasca.com/api/v1/explainer \
  -H "Authorization: Bearer $CHASCA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{ "input": "Why the sky is blue", "language": "ja", "voice": "chasca:kore" }'

Previews are plain MP3s at GET /v1/voices/:id/preview.mp3. In the SDK, call listVoices(). Voice ids from earlier versions (like chasca:nova) still work and map to the closest narrator.

Your own voice

Every plan can narrate in your own voice. In the app, open My voices, pick a language and read a short story out loud for one minute. Chasca cleans up the recording, learns how you sound and plays you a one-minute sample. From then on your voice sits above the narrators in every video’s options, at no extra cost.

Free includes 1 custom voice, Solo 1, Plus 3, Pro 5, Max 10, Team 30 and Enterprise 30. A voice speaks the language it was recorded in, so a video it narrates is in that language. Only you can use your voices, and deleting one deletes its recording.

Through the API, your ready voices are listed under custom in GET /v1/voices, with ids like clone:… that you pass as voice. The custom voices page walks through recording one.

Already recorded the narration? In the app, attach the recording on the Create page and tick Use as the narration: the video keeps every word as you said it and draws in time with it, for up to 1 minute on Free and 30 minutes on paid plans. See your own voiceover.

Pronunciations

A narrator guesses how to say a name it has never heard. To set one, add it in Settings, under Pronunciations: the word as it is written and how it sounds, such as Siobhan said “Shi-vawn” or SQL said “sequel”. Every new video says it that way, with every narrator and custom voice, while the board and captions keep your spelling. On a finished video, pick Pronunciation under Change one thing: only the scenes that say the word are recorded again, free. Through the API, send pronunciations when you create a video. See Pronunciations.

Pace

Every voice can be relaxed, balanced (default) or brisk. Narration is tuned to land around 140–160 words per minute, a comfortable pace for following along.