Skip to main content
Core.Today
|
Fish AudioFastUltra

Fish Audio S2.1 Pro

Fish Audio's current production TTS: 83 languages, bracketed natural-language emotion and tone control, 1M+ Voice Library voices and voice cloning. 61% listening-test win rate over S2 Pro with ~70 ms time-to-first-audio upstream. Billed per UTF-8 byte.

105 credits
per 1,000 Korean characters (0.034875 credits per UTF-8 byte; ~35 credits per 1,000 English characters)
83 languages from a single model (Korean, English, Japanese, Chinese, …)
Natural-language emotion and tone tags in brackets: [happy], [whispering], [laughing], [break]
1M+ Voice Library voices via reference_id, plus cloned voices
61% listening-test win rate over S2 Pro, ~70 ms time-to-first-audio upstream
mp3 / wav / opus output, speed and volume prosody control
Byte-proportional billing with no per-request minimum

Run it right now

Test this model instantly in the Console Playground — no code required

Sign in to try

Use with AI Assistant

Copy usage instructions for Claude, ChatGPT, or other AI

Quick Start

curl -X POST "https://api.core.today/v1/predictions" \
  -H "Content-Type: application/json" \
  -H "X-API-Key: cdt_your_api_key" \
  -d '{
  "model": "fishaudio/s2.1-pro",
  "input": {
    "text": "안녕하세요, 코어닷투데이입니다. 하나의 API 키로 이미지, 영상, 음성 생성 모델을 모두 연결해 보세요.",
    "reference_id": "2f06c7a428e9431fadd60af4dfe91763",
    "format": "mp3"
  }
}'

Voice Gallery

Showing 37 of 37

Every voice reads the same line. Play to compare timbre, then click an ID to copy it into reference_id.

Sample line (Korean): “안녕하세요, 코어닷투데이입니다. 하나의 API 키로 이미지, 영상, 음성 생성 모델을 모두 연결해 보세요.— “Hi, this is Core.Today. One API key connects you to image, video and speech models.

Fish Official Korean (15)

Designed by Fish rather than cloned from a person, so the rights position is the simplest here. Their registered descriptions are identical apart from gender and city, and the city is a label on the entry — nobody measured the accent — so pick these by ear.

지우F

Seoul female · chatbot replies and voice prompts

conversationalnatural
혜진F

Seoul female · chatbot replies and voice prompts

conversationalnatural
서윤F

Seoul female · chatbot replies and voice prompts

conversationalnatural
서연F

Seoul female · chatbot replies and voice prompts

conversationalnatural
하은F

Seoul female · chatbot replies and voice prompts

conversationalnatural
수아F

Registered as a Busan female conversational voice

conversationalregional
예린F

Registered as a Gyeongju female conversational voice

conversationalregional
유나F

Crisp young female · product and business narration

professionalclear
민준M

Seoul male · chatbot replies and voice prompts

conversationalnatural
시우M

Seoul male · chatbot replies and voice prompts

conversationalnatural
준서M

Seoul male · chatbot replies and voice prompts

conversationalnatural
도윤 (Doyoon)M

Seoul male · a different voice from Doyun below

conversationalnatural
도윤 (Doyun)M

Seoul male · a different voice from Doyoon above

conversationalnatural
재민M

Registered as a Busan male conversational voice

conversationalregional
태오M

Registered as a Gyeongju male conversational voice

conversationalregional

Korean community (18)

Uploaded by Fish users, and the place to look for a specific job — narration, shorts, advertising reads, interview hosting. Voices cloned from identifiable people are not listed here.

차분한 내레이션F

Documentary and reflective narration

calmclearprofessional
기본 나레이션 (남)M

News reads and educational narration

steadymeasuredauthoritative
부드러운 내레이터M

Warm storytelling and essay reads

warmgentleempathetic
다큐 나레이션F

Documentary and factual narration

calmprofessionalclear
긍정 아나운서F

Explainer videos and course narration

articulateprofessionalfriendly
따뜻한 여성F

Conversation and storytelling

warmrelaxedexpressive
20대 여성 (광고)F

Product ads and informational reads

smoothcalmpersuasive
나긋나긋 쇼츠F

Shorts and social clips

brightenergeticfriendly
효정 (팟캐스트)F

Podcasts and conversational content

smoothfriendlynatural
애덤 (광고)M

Advertising and promo reads

energeticconfidentpersuasive
유라F

Composed female narration

calmsmoothprofessional
진우M

Storytelling and long-form reads

calmsmoothnarrative
보이스1M

Entertainment and character lines

brightenergeticenthusiastic
30대 남자 인터뷰어M

Interview hosting and course content

calmclearfriendly
정보성 유튜버 (남)M

Fast-paced explainer videos

energeticfastconfident
20대 여성 쇼츠F

Beauty, tutorials and social

brightenergeticfriendly
호기요M

Educational content and narration

calmclearfriendly
성현M

Intimate conversation and ASMR

warmgentleintimate

Robot and character (4)

Registered as English, but measured on Korean: our gateway synthesized a Korean line, our own ASR transcribed it back, and the accuracy score is how closely that transcript matched (1.0 = exact). Voices that failed are not listed — one Spanish-registered robot scored 0.0 and produced no Korean at all.

장난꾸러기 로봇N

Playful robot character · Korean accuracy 0.97

high-pitchedenergeticmechanical
활기찬 로봇N

Game and animation robot · Korean accuracy 0.97

expressiveenergetichigh-pitched
레트로 컴퓨터M

Retro computer voice · Korean accuracy 0.94

monotoneelectronicretro
안내용 로봇M

Announcements and instructions · Korean accuracy 0.85

monotoneclearneutral

Parameters

ParameterTypeRequiredDefaultDescription
textstringYes-Text to synthesize (UTF-8). Billed by UTF-8 bytes — one Korean character is 3 bytes. Emotion, tone and effect cues go in brackets before the text they steer, e.g. [happy] Welcome!, [whispering] …, [laughing], [break].
reference_idstringNo2f06c7a428e9431fadd60af4dfe91763Voice ID (32-hex id from the Fish Audio Voice Library). 37 curated voices (15 Fish Official Korean, 18 Korean community, 4 robot/character) can be previewed and copied from the Voice Gallery on this model's Core.Today Docs page (docs/models/fishaudio/…); any other public or cloned voice id works too — you are responsible for the rights to the voice you pass.
formatstringNomp3Output audio format.
mp3wavopus
mp3_bitrateintegerNo128MP3 bitrate in kbps (mp3 only).
64128192
speednumberNo1.0Speaking rate multiplier, 0.5–2.0 (1.0 = default).
volumenumberNo0Volume adjustment in dB, -20 to 20 (0 = default).
latencystringNobalancedbalanced favors low latency (default); normal favors stability — a good choice for batch generation.
balancednormal
normalizebooleanNotrueExpand numbers, dates and units into spoken form.
temperaturenumberNo0.7Sampling temperature, 0.1–1.0. Lower is more consistent, higher more expressive.
top_pnumberNo0.7Nucleus sampling probability mass, 0.1–1.0.
chunk_lengthintegerNo200Internal chunk length, 100–300. Affects phrasing of long passages.

Common Parameters

Common parameters used when calling POST /v1/predictions.

ParameterTypeRequiredDefaultDescription
modelstringYes-Model identifier
inputobjectYes-Object containing the model-specific parameters from the table above
output_folderstringNo-Folder path for output files (max 256 chars, '..' not allowed)
webhook_urlstringNo-Webhook URL to call on completion
is_publicbooleanNofalseIf true, output files are also available via permanent public URLs

Examples

Core.Today intro (calm narration voice)

The line every gallery voice reads, rendered with the default voice.

curl -X POST "https://api.core.today/v1/predictions" \
  -H "Content-Type: application/json" \
  -H "X-API-Key: cdt_your_api_key" \
  -d '{
  "model": "fishaudio/s2.1-pro",
  "input": {
    "text": "안녕하세요, 코어닷투데이입니다. 하나의 API 키로 이미지, 영상, 음성 생성 모델을 모두 연결해 보세요.",
    "reference_id": "2f06c7a428e9431fadd60af4dfe91763",
    "format": "mp3"
  }
}'

Emotion tags

Bracketed natural-language cues steer tone sentence by sentence.

curl -X POST "https://api.core.today/v1/predictions" \
  -H "Content-Type: application/json" \
  -H "X-API-Key: cdt_your_api_key" \
  -d '{
  "model": "fishaudio/s2.1-pro",
  "input": {
    "text": "[excited] 드디어 새 모델이 나왔어요! [whispering] 그런데 가격은 그대로예요. [laughing]",
    "reference_id": "4e118bfbb83e401c84699c09b5f08257"
  }
}'

Tips & Best Practices

1The 15 Fish Official Korean voices (지우, 민준, …) are designed by Fish rather than cloned from a person, which makes their rights position the simplest — a good baseline to compare against
2The 4 robot voices are registered as English but were measured on Korean: our gateway synthesized a Korean line and our own ASR transcribed it back at 0.85–0.97 similarity. Voices that failed that test are not in the gallery
3Voices cloned from named characters or identifiable voice actors are deliberately absent. You can still pass any reference_id to the API — the rights to that voice are yours to clear
4Put emotion cues at the start of a sentence ([happy] …); tone and effect tags like [whispering] or [laughing] can go anywhere
5Korean is 3 UTF-8 bytes per character — 1,000 Korean characters cost about 105 credits, 1,000 English characters about 35
6Copy a reference_id from the Voice Gallery at the bottom of this docs page; every sample reads the same Core.Today line so you can compare timbre
7Use latency=normal for batch jobs where stability matters more than time-to-first-audio
8Keep normalize=true for numbers and dates; turn it off only when you spell things out yourself

Use Cases

Korean narration for shorts, ads and explainer videos
Multilingual product voice-overs from one model
Audiobooks and long-form storytelling with emotion tags
Announcements and IVR prompts
Podcast intros and character voices