# Core.Today AI API — Audio & TTS Models

> Text-to-speech, music generation and audio utility models (MiniMax Speech, Clova Voice, Suno) available through the Core.Today unified API.

Source: https://console.core.today/docs/audio-models
This file: https://console.core.today/llms/audio-models.txt
All models: https://console.core.today/llms.txt

## API Usage

Base URL: https://api.core.today/v1
Auth header: X-API-Key: YOUR_API_KEY

1. POST /predictions with {"model": "<model id>", "input": {...}} -> returns job_id
2. GET /predictions/{job_id} -> poll until status is "completed" or "failed"
3. result contains output URL(s); add "is_public": true for a permanent public URL

## Models (32)

### Bark — `suno-ai/bark`

Suno's text-prompted generative audio model. Produces speech with nonverbal sounds like [laughs] and [sighs], plus music and sound effects, in 100+ speaker presets across 13 languages. Returns audio plus an optional .npz history file for voice continuity.

- Provider: Suno
- Credits: 190 (per generation)
- Speed: slow / Quality: standard
- Optional params: prompt=Hello, my name is Suno. And, uh — and I like pizza. [laughs] But I also have other interests such as playing tic tac toe., history_prompt, custom_history_prompt, text_temp=0.7, waveform_temp=0.7, output_full=false
- Example input:
```json
{
  "model": "suno-ai/bark",
  "input": {
    "prompt": "Hello, my name is Suno. And, uh — and I like pizza. [laughs] But I also have other interests such as playing tic tac toe.",
    "history_prompt": "en_speaker_6",
    "text_temp": 0.7,
    "waveform_temp": 0.7
  }
}
```
- Full docs: https://console.core.today/docs/models/suno-ai/bark

### Chatterbox — `resemble-ai/chatterbox`

Resemble AI's production-grade open-source TTS with unique emotion exaggeration control and instant voice cloning from a short reference audio. MIT-licensed and benchmarked against leading closed-source systems.

- Provider: Resemble AI
- Credits: 59 (per 1000 characters (0.057 credits/char, billed per character))
- Speed: fast / Quality: high
- Required params: prompt (string)
- Optional params: audio_prompt, exaggeration=0.5, cfg_weight=0.5, temperature=0.8, seed=0
- Example input:
```json
{
  "model": "resemble-ai/chatterbox",
  "input": {
    "prompt": "We're excited to introduce Chatterbox, our first production-grade open source TTS model!",
    "exaggeration": 0.8,
    "cfg_weight": 0.5
  }
}
```
- Full docs: https://console.core.today/docs/models/resemble-ai/chatterbox

### Chatterbox Multilingual — `resemble-ai/chatterbox-multilingual`

Chatterbox open-source TTS in 23 languages with instant voice cloning and emotion exaggeration control. Max 300 characters per request.

- Provider: Resemble AI
- Credits: 7 (per generation (max 300 characters))
- Speed: fast / Quality: high
- Required params: text (string)
- Optional params: language=en, reference_audio, exaggeration=0.5, temperature=0.8, cfg_weight=0.5, seed=0
- Example input:
```json
{
  "model": "resemble-ai/chatterbox-multilingual",
  "input": {
    "text": "안녕하세요, 코어닷투데이입니다. 오늘도 좋은 하루 보내세요!",
    "language": "ko",
    "exaggeration": 0.5
  }
}
```
- Full docs: https://console.core.today/docs/models/resemble-ai/chatterbox-multilingual

### Chatterbox Turbo — `resemble-ai/chatterbox-turbo`

Resemble AI's fastest open-source TTS without sacrificing quality. 20 pre-made voices, paralinguistic tags like [sigh] and [chuckle], and optional instant voice cloning from 5s+ reference audio. Max 500 characters per request.

- Provider: Resemble AI
- Credits: 59 (per 1000 characters (0.057 credits/char, billed per character))
- Speed: fast / Quality: high
- Required params: text (string)
- Optional params: voice=Andy, reference_audio, temperature=0.8, top_p=0.95, top_k=1000, repetition_penalty=1.2, seed
- Example input:
```json
{
  "model": "resemble-ai/chatterbox-turbo",
  "input": {
    "text": "Oh, that's hilarious! [chuckle] Anyway, we do have a new model in store. Would you like me to get some prices for you?",
    "voice": "Laura",
    "temperature": 0.8
  }
}
```
- Full docs: https://console.core.today/docs/models/resemble-ai/chatterbox-turbo

### Gemini 3.1 Flash TTS — `google/gemini-3.1-flash-tts`

Google Gemini 3.1 Flash native-audio TTS via Replicate. Style instructions (separate from the spoken text) plus 30 preset voices and 40+ language/locale codes, with inline markup tags for expressive delivery ([sigh], [whispering], [shouting], etc.).

- Provider: Google
- Credits: 299 (per 1000 characters (input text + generated speech))
- Speed: fast / Quality: high
- Required params: text (string)
- Optional params: prompt=Say the following., voice=Kore, language_code=en-US
- Example input:
```json
{
  "model": "google/gemini-3.1-flash-tts",
  "input": {
    "prompt": "Say this in a calm, professional tone, like a documentary narrator.",
    "text": "오늘 소개할 제품은 최신 무선 이어폰입니다. 뛰어난 음질과 편안한 착용감을 동시에 제공합니다.",
    "voice": "Kore",
    "language_code": "ko-KR"
  }
}
```
- Full docs: https://console.core.today/docs/models/google/gemini-3.1-flash-tts

### Incredibly Fast Whisper — `vaibhavs10/incredibly-fast-whisper`

Whisper large-v3 optimized for speed (38M+ runs) — transcribes roughly 150 minutes of audio in under 100 seconds using batched inference. Chunk-level or word-level timestamps.

- Provider: Whisper
- Credits: 10 (per run)
- Speed: fast / Quality: ultra
- Required params: audio (string)
- Optional params: task=transcribe, language=None, batch_size=24, timestamp=chunk, diarise_audio=false, hf_token
- Example input:
```json
{
  "model": "vaibhavs10/incredibly-fast-whisper",
  "input": {
    "audio": "https://example.com/podcast-episode.mp3",
    "task": "transcribe",
    "timestamp": "word"
  }
}
```
- Full docs: https://console.core.today/docs/models/vaibhavs10/incredibly-fast-whisper

### Suno Music V5.5 — `suno/music-v5-5`

Suno's latest model, with the highest audio quality and richest arrangements. Creates two complete songs from a text description, or from exact lyrics with style and title in custom mode. Returns audio, cover image, and metadata for each track.

- Provider: Suno
- Credits: 140 (per generation (2 songs))
- Speed: medium / Quality: ultra
- Required params: customMode (boolean), instrumental (boolean)
- Optional params: prompt, style, title, negativeTags, vocalGender, styleWeight, weirdnessConstraint, audioWeight
- Example input:
```json
{
  "model": "suno/music-v5-5",
  "input": {
    "customMode": false,
    "instrumental": false,
    "prompt": "A dreamy synthwave track about driving through a neon city at night"
  }
}
```
- Full docs: https://console.core.today/docs/models/suno/music-v5-5

### Suno Music V5 — `suno/music-v5`

Suno V5 music generation with improved audio quality and musicality. Creates two complete songs from a text description, or from exact lyrics with style and title in custom mode. Returns audio, cover image, and metadata for each track.

- Provider: Suno
- Credits: 140 (per generation (2 songs))
- Speed: medium / Quality: high
- Required params: customMode (boolean), instrumental (boolean)
- Optional params: prompt, style, title, negativeTags, vocalGender, styleWeight, weirdnessConstraint, audioWeight
- Example input:
```json
{
  "model": "suno/music-v5",
  "input": {
    "customMode": false,
    "instrumental": false,
    "prompt": "A dreamy synthwave track about driving through a neon city at night"
  }
}
```
- Full docs: https://console.core.today/docs/models/suno/music-v5

### Suno Music V4.5 — `suno/music-v4-5`

Suno V4.5 music generation. Creates two complete songs from a text description, or from exact lyrics with style and title in custom mode. Returns audio, cover image, and metadata for each track.

- Provider: Suno
- Credits: 140 (per generation (2 songs))
- Speed: medium / Quality: high
- Required params: customMode (boolean), instrumental (boolean)
- Optional params: prompt, style, title, negativeTags, vocalGender, styleWeight, weirdnessConstraint, audioWeight
- Example input:
```json
{
  "model": "suno/music-v4-5",
  "input": {
    "customMode": false,
    "instrumental": false,
    "prompt": "A dreamy synthwave track about driving through a neon city at night"
  }
}
```
- Full docs: https://console.core.today/docs/models/suno/music-v4-5

### MiniMax Music 2.6 — `minimax/music-2.6`

Generate full-length songs or instrumentals (up to ~6 minutes) from a text prompt. 99%+ accurate BPM/key control, 14+ structure tags, auto-generated lyrics, and instrumental-only mode.

- Provider: MiniMax
- Credits: 350 (per generation (1 audio file))
- Speed: medium / Quality: high
- Optional params: prompt=, lyrics=, is_instrumental=false, lyrics_optimizer=false, sample_rate=44100, bitrate=256000, audio_format=mp3
- Example input:
```json
{
  "model": "minimax/music-2.6",
  "input": {
    "prompt": "E minor, 90 BPM, acoustic guitar ballad, male vocal, emotional, intimate studio feel",
    "lyrics": "[Verse]\n밤하늘의 별을 세다가\n너의 이름을 떠올렸어\n\n[Chorus]\n아직도 기억해 그날의 노래\n바람에 실려 오는 멜로디\n\n[Outro]\n그날의 노래...",
    "audio_format": "mp3",
    "bitrate": 256000,
    "sample_rate": 44100
  }
}
```
- Full docs: https://console.core.today/docs/models/minimax/music-2.6

### MiniMax Music 2.5 — `minimax/music-2.5`

Generate full-length songs (up to ~5 minutes) with vocals, lyrics, and rich instrumentation. 14 structure tags, style-aware mixing, and an expanded instrument library including orchestral and traditional instruments.

- Provider: MiniMax
- Credits: 350 (per generation (1 audio file))
- Speed: medium / Quality: high
- Required params: lyrics (string)
- Optional params: prompt=, sample_rate=44100, bitrate=256000, audio_format=mp3
- Example input:
```json
{
  "model": "minimax/music-2.5",
  "input": {
    "prompt": "Folk country, fingerpicked acoustic guitar, warm male vocal, nostalgic, intimate studio feel",
    "lyrics": "[Verse]\nOld screen door don't close right anymore\nCreaks like my knees on a cold morning\n\n[Chorus]\nBut time don't ask permission\nAnd rivers don't run backwards, friend\n\n[Outro]\n(Harmonica fades out)",
    "audio_format": "mp3",
    "bitrate": 256000,
    "sample_rate": 44100
  }
}
```
- Full docs: https://console.core.today/docs/models/minimax/music-2.5

### MiniMax Music Cover — `minimax/music-cover`

Reimagine any song in a different style. The model extracts the melodic structure from the input audio and regenerates the track — the melody and duration stay the same, but voice, instruments, genre, and arrangement can all change.

- Provider: MiniMax
- Credits: 700 (per generation (1 audio file))
- Speed: medium / Quality: high
- Required params: prompt (string), audio_url (string)
- Optional params: lyrics=, sample_rate=44100, bitrate=256000, audio_format=mp3
- Example input:
```json
{
  "model": "minimax/music-cover",
  "input": {
    "audio_url": "https://example.com/original-song.mp3",
    "prompt": "Jazz arrangement, saxophone lead, smooth female vocal, mellow piano chords, late night club",
    "audio_format": "mp3",
    "bitrate": 256000,
    "sample_rate": 44100
  }
}
```
- Full docs: https://console.core.today/docs/models/minimax/music-cover

### Qwen3 TTS — `qwen/qwen3-tts`

Alibaba's unified TTS with three modes: preset speakers (custom_voice), instant voice cloning from reference audio (voice_clone), and creating a brand-new voice from a text description (voice_design).

- Provider: Qwen
- Credits: 47 (per 1000 characters (0.045 credits/char, billed per character))
- Speed: fast / Quality: high
- Required params: text (string)
- Optional params: mode=custom_voice, language=auto, speaker=Serena, voice_description, reference_audio, reference_text, style_instruction
- Example input:
```json
{
  "model": "qwen/qwen3-tts",
  "input": {
    "mode": "custom_voice",
    "text": "안녕하세요, 코어닷투데이입니다. 무엇을 도와드릴까요?",
    "speaker": "Sohee",
    "language": "auto"
  }
}
```
- Full docs: https://console.core.today/docs/models/qwen/qwen3-tts

### Inworld Realtime TTS 2 — `inworld/realtime-tts-2`

Inworld's most expressive TTS with natural-language steering — place bracketed instructions like [speak quickly] before the text they apply to. Real-time latency and 15+ language support.

- Provider: Inworld
- Credits: 59 (per 1000 characters (0.057 credits/char, billed per character))
- Speed: fast / Quality: high
- Required params: text (string)
- Optional params: voice_id=Ashley, language=auto, speaking_rate=0, temperature=0, audio_format=mp3, sample_rate=48000, text_normalization=auto
- Example input:
```json
{
  "model": "inworld/realtime-tts-2",
  "input": {
    "text": "[speak quickly with a clear and direct manner] Your confirmation number is 8 4 7 2 9. Your order will arrive by FRIDAY at 3:45 PM.",
    "voice_id": "Dennis",
    "audio_format": "mp3"
  }
}
```
- Full docs: https://console.core.today/docs/models/inworld/realtime-tts-2

### Suno SFX V5 — `suno/sfx-v5`

Suno V5 sound effect generation. Creates two short sound effect variants from a text description, with optional loop mode, tempo, and musical key controls. Ideal for UI sounds, game audio, and video foley.

- Provider: Suno
- Credits: 29 (per generation (2 variants))
- Speed: fast / Quality: high
- Required params: prompt (string)
- Optional params: soundLoop, soundTempo, soundKey, grabLyrics
- Example input:
```json
{
  "model": "suno/sfx-v5",
  "input": {
    "prompt": "single soft door knock, dry room"
  }
}
```
- Full docs: https://console.core.today/docs/models/suno/sfx-v5

### MiniMax Speech 2.8 HD — `minimax/speech-2.8-hd`

Ranked #1 on Artificial Analysis Speech Arena and Hugging Face TTS Arena. Broadcast-quality TTS with autoregressive Transformer + Flow-VAE decoder, 32+ languages, voice cloning, natural interjections, and emotion control.

- Provider: MiniMax
- Credits: 237 (per 1000 characters (0.225 credits/char, billed per character))
- Speed: medium / Quality: ultra
- Required params: text (string)
- Optional params: voice_id=English_Wiselady, speed=1, volume=1, pitch=0, emotion=auto, english_normalization=false, sample_rate=32000, bitrate=128000, audio_format=mp3, channel=mono, subtitle_enable=false, language_boost=None
- Example input:
```json
{
  "model": "minimax/speech-2.8-hd",
  "input": {
    "text": "안녕하세요, 코어닷투데이입니다. (sighs) 오늘은 특별한 이야기를 들려드리려고 합니다. <#0.5#> AI가 만드는 새로운 세상, 함께 경험해 보시겠어요?",
    "voice_id": "Korean_SweetGirl",
    "emotion": "calm",
    "speed": 0.9,
    "pitch": 0,
    "sample_rate": 32000,
    "language_boost": "Korean"
  }
}
```
- Full docs: https://console.core.today/docs/models/minimax/speech-2.8-hd

### MiniMax Speech 2.8 Turbo — `minimax/speech-2.8-turbo`

Low-latency MiniMax Speech 2.8 Turbo with under 250ms latency, 40+ languages, voice cloning, natural interjections, and real-time pricing. Ideal for interactive and real-time applications.

- Provider: MiniMax
- Credits: 142 (per 1000 characters (0.135 credits/char, billed per character))
- Speed: fast / Quality: high
- Required params: text (string)
- Optional params: voice_id=English_Wiselady, speed=1, volume=1, pitch=0, emotion=auto, english_normalization=false, sample_rate=32000, bitrate=128000, audio_format=mp3, channel=mono, subtitle_enable=false, language_boost=None
- Example input:
```json
{
  "model": "minimax/speech-2.8-turbo",
  "input": {
    "text": "안녕하세요! (laughs) 코어닷투데이에 오신 것을 환영합니다. <#0.3#> 최고의 AI 음성을 빠르게 경험해 보세요!",
    "voice_id": "Korean_CheerfulLittleSister",
    "emotion": "happy",
    "speed": 1,
    "language_boost": "Korean"
  }
}
```
- Full docs: https://console.core.today/docs/models/minimax/speech-2.8-turbo

### MiniMax Speech 2.6 HD — `minimax/speech-2.6-hd`

Studio-quality multilingual text-to-speech with nuanced prosody, emotion control, and premium voices for professional applications.

- Provider: MiniMax
- Credits: 237 (per 1000 characters (0.225 credits/char, billed per character))
- Speed: medium / Quality: ultra
- Required params: text (string)
- Optional params: voice_id=English_Wiselady, speed=1, volume=1, pitch=0, emotion=auto, english_normalization=false, sample_rate=32000, bitrate=128000, audio_format=mp3, channel=mono, subtitle_enable=false, language_boost=None
- Example input:
```json
{
  "model": "minimax/speech-2.6-hd",
  "input": {
    "text": "안녕하세요, 코어닷투데이입니다. 오늘도 여러분과 함께할 수 있어 기쁩니다. 최고의 AI 서비스를 경험해 보세요.",
    "voice_id": "Korean_CalmGentleman",
    "emotion": "calm",
    "speed": 0.9,
    "pitch": 0,
    "sample_rate": 32000,
    "language_boost": "Korean"
  }
}
```
- Full docs: https://console.core.today/docs/models/minimax/speech-2.6-hd

### MiniMax Speech 2.6 Turbo — `minimax/speech-2.6-turbo`

Fast multilingual text-to-speech with emotional control, optimized for real-time applications with low latency.

- Provider: MiniMax
- Credits: 142 (per 1000 characters (0.135 credits/char, billed per character))
- Speed: fast / Quality: high
- Required params: text (string)
- Optional params: voice_id=English_Wiselady, speed=1, volume=1, pitch=0, emotion=auto, english_normalization=false, sample_rate=32000, bitrate=128000, audio_format=mp3, channel=mono, subtitle_enable=false, language_boost=None
- Example input:
```json
{
  "model": "minimax/speech-2.6-turbo",
  "input": {
    "text": "안녕하세요, 코어닷투데이입니다. 근처에 맛집 3곳을 찾았어요. 예약해 드릴까요?",
    "voice_id": "Korean_FriendlyBigSister",
    "emotion": "happy",
    "speed": 1.1,
    "language_boost": "Korean"
  }
}
```
- Full docs: https://console.core.today/docs/models/minimax/speech-2.6-turbo

### MiniMax Speech-02-Turbo — `minimax/speech-02-turbo`

Low-latency text-to-speech model with multilingual support, emotional voice control, and 300+ voice options.

- Provider: MiniMax
- Credits: 142 (per 1000 characters (0.135 credits/char, billed per character))
- Speed: fast / Quality: high
- Required params: text (string)
- Optional params: voice_id=English_Wiselady, speed=1, volume=1, pitch=0, emotion=auto, english_normalization=false, sample_rate=32000, bitrate=128000, audio_format=mp3, channel=mono, subtitle_enable=false, language_boost=None
- Example input:
```json
{
  "model": "minimax/speech-02-turbo",
  "input": {
    "text": "안녕하세요! 코어닷투데이에 오신 것을 환영합니다. 무엇을 도와드릴까요?",
    "voice_id": "Korean_CalmLady",
    "emotion": "happy",
    "speed": 1,
    "language_boost": "Korean"
  }
}
```
- Full docs: https://console.core.today/docs/models/minimax/speech-02-turbo

### Sonilo v1.1 Text to Music — `sonilo/v1.1/text-to-music`

Sonilo v1.1 text-to-music via Fal.AI. Generates up to 3 distinct music tracks (up to 600 seconds each) from a text description of the desired sound.

- Provider: Sonilo
- Credits: 520 (per second per generated track)
- Speed: fast / Quality: standard
- Required params: prompt (string)
- Optional params: duration=90, num_samples=1
- Example input:
```json
{
  "model": "sonilo/v1.1/text-to-music",
  "input": {
    "prompt": "A blend of R&B warmth, soul depth, neo-soul texture, gospel spirit, pop clarity, and jazz sophistication.",
    "duration": 90,
    "num_samples": 1
  }
}
```
- Full docs: https://console.core.today/docs/models/sonilo/v1.1/text-to-music

### Inworld TTS 1.5 Max — `inworld/tts-1.5-max`

Inworld's highest-quality realtime TTS with under 200ms latency. Supports SSML break tags for pauses, emotion markups like [happy], and 15 languages.

- Provider: Inworld
- Credits: 24 (per 1000 characters (0.023 credits/char, billed per character))
- Speed: fast / Quality: high
- Required params: text (string)
- Optional params: voice_id=Ashley, speaking_rate=0, temperature=0, audio_format=mp3, sample_rate=48000, text_normalization=auto
- Example input:
```json
{
  "model": "inworld/tts-1.5-max",
  "input": {
    "text": "[happy] Welcome back! <break time=\"0.5s\" /> Your order shipped this morning and arrives tomorrow.",
    "voice_id": "Ashley"
  }
}
```
- Full docs: https://console.core.today/docs/models/inworld/tts-1.5-max

### Clova Voice TTS Premium — `ncp-clova/tts-premium`

NAVER Clova Voice Premium TTS with 108 voices across 6 languages. High-quality Korean voice synthesis with emotion control, Pro voices, and bilingual support.

- Provider: NCP Clova
- Credits: 153 (per 1,000 characters (0.15 credits/char, billed by exact character count))
- Speed: fast / Quality: high
- Required params: text (string), speaker (string)
- Optional params: volume=0, speed=0, pitch=0, emotion=0, emotion-strength=1, format=mp3
- Example input:
```json
{
  "model": "ncp-clova/tts-premium",
  "input": {
    "text": "안녕하세요, 코어닷투데이입니다. 최고의 AI 서비스를 경험해 보세요!",
    "speaker": "vara",
    "emotion": 2,
    "emotion-strength": 2,
    "speed": 0,
    "format": "mp3"
  }
}
```
- Full docs: https://console.core.today/docs/models/ncp-clova/tts-premium

### ElevenLabs Turbo v2.5 — `elevenlabs/turbo-v2.5`

High-quality, low-latency ElevenLabs text-to-speech in 32 languages. The same 26 premium voices as v3 at half the price, optimized for real-time and high-volume use.

- Provider: ElevenLabs
- Credits: 119 (per 1000 characters (0.113 credits/char, billed per character))
- Speed: fast / Quality: high
- Required params: prompt (string)
- Optional params: speed=1, style=0, voice=Rachel, next_text=, stability=0.5, language_code=en, previous_text=, similarity_boost=0.75
- Example input:
```json
{
  "model": "elevenlabs/turbo-v2.5",
  "input": {
    "prompt": "안녕하세요! 주문하신 상품이 내일 오후에 도착할 예정입니다. 더 도와드릴 일이 있을까요?",
    "voice": "Sarah",
    "language_code": "ko",
    "speed": 1.05
  }
}
```
- Full docs: https://console.core.today/docs/models/elevenlabs/turbo-v2.5

### ElevenLabs v3 — `elevenlabs/v3`

ElevenLabs' most expressive text-to-speech model. 26 premium voices, inline audio tags like [laughs] and [whispers], fine-grained style and stability controls, and 70+ language support.

- Provider: ElevenLabs
- Credits: 237 (per 1000 characters (0.225 credits/char, billed per character))
- Speed: medium / Quality: ultra
- Required params: prompt (string)
- Optional params: voice=Rachel, stability=0.5, similarity_boost=0.75, style=0, speed=1, previous_text=, next_text=, language_code=en
- Example input:
```json
{
  "model": "elevenlabs/v3",
  "input": {
    "prompt": "[whispers] Something moved in the darkness. [pause] Then, out of nowhere... [excited] a tiny kitten jumped onto the table! [laughs]",
    "voice": "James",
    "stability": 0.4,
    "language_code": "en"
  }
}
```
- Full docs: https://console.core.today/docs/models/elevenlabs/v3

### ElevenLabs v2 Multilingual — `elevenlabs/v2-multilingual`

ElevenLabs Multilingual v2 text-to-speech in over 30 languages. Stable, proven voice quality with the same premium voice lineup and fine-grained voice settings.

- Provider: ElevenLabs
- Credits: 237 (per 1000 characters (0.225 credits/char, billed per character))
- Speed: medium / Quality: high
- Required params: prompt (string)
- Optional params: speed=1, style=0, voice=Rachel, next_text=, stability=0.5, language_code=en, previous_text=, similarity_boost=0.75
- Example input:
```json
{
  "model": "elevenlabs/v2-multilingual",
  "input": {
    "prompt": "Demain, dès l'aube, à l'heure où blanchit la campagne, je partirai.",
    "voice": "Aria",
    "language_code": "fr",
    "stability": 0.6
  }
}
```
- Full docs: https://console.core.today/docs/models/elevenlabs/v2-multilingual

### Sonilo v1.1 Video to Sound Effects — `sonilo/v1.1/video-to-sound-effects`

Sonilo v1.1 video-to-sound-effects via Fal.AI. Adds AI-generated sound (ambience, effects, foley) to an input video — auto-captions the scene if no prompt is given, or accepts per-segment sound descriptions for finer control.

- Provider: Sonilo
- Credits: 310 (per video (flat rate, regardless of length))
- Speed: fast / Quality: standard
- Required params: video_url (string)
- Optional params: prompt, segments, audio_format=aac
- Example input:
```json
{
  "model": "sonilo/v1.1/video-to-sound-effects",
  "input": {
    "video_url": "https://storage.googleapis.com/falserverless/model_tests/video_models/mmaudio_input.mp4",
    "audio_format": "aac"
  }
}
```
- Full docs: https://console.core.today/docs/models/sonilo/v1.1/video-to-sound-effects

### Suno Vocal Separation — `suno/vocal-separation`

Separate a Suno-generated track into clean vocal and instrumental stems. Takes the taskId and audioId from a previous Suno music generation and returns separated vocalUrl/instrumentalUrl audio files.

- Provider: Suno
- Credits: 120 (per separation)
- Speed: fast / Quality: high
- Required params: taskId (string), audioId (string)
- Example input:
```json
{
  "model": "suno/vocal-separation",
  "input": {
    "taskId": "5c7998a1b2c3d4e5f60718293a4b5c6d",
    "audioId": "34fa3e86-2fc8-4f8a-8ea3-f58b664bde51"
  }
}
```
- Full docs: https://console.core.today/docs/models/suno/vocal-separation

### MiniMax Voice Cloning — `minimax/voice-cloning`

Clone any voice from a 10-second to 5-minute audio sample. Returns a custom voice_id you can pass to MiniMax speech models, plus a preview clip synthesized with the cloned voice.

- Provider: MiniMax
- Credits: 6980 (per clone (one-time; returns a reusable voice_id))
- Speed: medium / Quality: high
- Required params: voice_file (string)
- Optional params: model=speech-02-turbo, accuracy=0.7, need_noise_reduction=false, need_volume_normalization=false
- Example input:
```json
{
  "model": "minimax/voice-cloning",
  "input": {
    "voice_file": "https://example.com/narrator-sample.wav",
    "model": "speech-02-turbo",
    "accuracy": 0.7,
    "need_noise_reduction": false,
    "need_volume_normalization": false
  }
}
```
- Full docs: https://console.core.today/docs/models/minimax/voice-cloning

### Whisper — `openai/whisper`

OpenAI's Whisper large-v3 speech recognition (144M+ runs) — the standard for transcription. Automatic language detection across ~100 languages, English translation, and plain text / SRT / VTT output formats.

- Provider: OpenAI
- Credits: 10 (per run (runtime grows with audio length))
- Speed: medium / Quality: ultra
- Required params: audio (string)
- Optional params: transcription=plain text, translate=false, language=auto, temperature=0, patience, suppress_tokens=-1, initial_prompt, condition_on_previous_text=true, temperature_increment_on_fallback=0.2, compression_ratio_threshold=2.4, logprob_threshold=-1, no_speech_threshold=0.6
- Example input:
```json
{
  "model": "openai/whisper",
  "input": {
    "audio": "https://example.com/meeting.mp3",
    "language": "auto",
    "transcription": "plain text"
  }
}
```
- Full docs: https://console.core.today/docs/models/openai/whisper

### Whisper Diarization — `thomasmol/whisper-diarization`

Whisper transcription with speaker diarization (8M+ runs) — returns who said what, with per-segment speaker labels and timestamps. The go-to for meetings and interviews.

- Provider: Whisper
- Credits: 7 (per run)
- Speed: fast / Quality: high
- Optional params: prompt, file_string, file_url, file, num_speakers, translate=false, language
- Example input:
```json
{
  "model": "thomasmol/whisper-diarization",
  "input": {
    "file_url": "https://example.com/interview.mp3",
    "num_speakers": 2,
    "language": "ko",
    "prompt": "코어닷투데이, API, 크레딧"
  }
}
```
- Full docs: https://console.core.today/docs/models/thomasmol/whisper-diarization

### XTTS-v2 — `lucataco/xtts-v2`

Coqui XTTS-v2 multilingual voice-cloning TTS. Clone a voice from a single short audio sample and speak in 16 languages — one of the most popular open-source voice cloning models.

- Provider: Coqui
- Credits: 26 (per generation)
- Speed: medium / Quality: standard
- Required params: speaker (string)
- Optional params: text=Hi there, I'm your new voice clone. Try your best to upload quality audio, language=en, cleanup_voice=false
- Example input:
```json
{
  "model": "lucataco/xtts-v2",
  "input": {
    "speaker": "https://example.com/voice-sample.wav",
    "text": "안녕하세요, 이것은 제 목소리로 만든 한국어 음성입니다.",
    "language": "ko",
    "cleanup_voice": true
  }
}
```
- Full docs: https://console.core.today/docs/models/lucataco/xtts-v2