AI TOOLS RADAR
Invia
Tutti i modelli / MINIMAX
minimax logo
minimax

MiniMax: Speech 2.8 Turbo

Descrizione della fonte (inglese)

MiniMax Speech 2.8 Turbo is a text-to-speech model from MiniMax. It is suited for applications that generate spoken audio from text and accepts arbitrary MiniMax voice IDs.

Vedi la fonte su OpenRouter
Panoramica

Specifiche del modello

Contesto
Non indicato
Output massimo
Non indicato
Architettura
text->speech
Tokenizer
Other
Limite di conoscenza
Non indicato
Moderato
No
OPENROUTER

Prezzi completi

Tariffe sincronizzate da OpenRouter, per milione di token.

Caratteri
$60
per milione di caratteri
API

Configurazione del modello

Voci supportate

English_expressive_narratorEnglish_radiant_girlEnglish_magnetic_voiced_manEnglish_compelling_lady1English_Aussie_BlokeEnglish_captivating_female1English_Upbeat_WomanEnglish_Trustworth_ManEnglish_CalmWomanEnglish_UpsetGirlEnglish_Gentle-voiced_manEnglish_Whispering_girlEnglish_Diligent_ManEnglish_Graceful_LadyEnglish_ReservedYoungManEnglish_PlayfulGirlEnglish_ManWithDeepVoiceEnglish_MaturePartnerEnglish_FriendlyPersonEnglish_MatureBossEnglish_DebatorEnglish_LovelyGirlEnglish_SteadymentorEnglish_Deep-VoicedGentlemanEnglish_WiseladyEnglish_CaptivatingStorytellerEnglish_DecentYoungManEnglish_SentimentalLadyEnglish_ImposingMannerEnglish_SadTeenEnglish_PassionateWarriorEnglish_WiseScholarEnglish_Soft-spokenGirlEnglish_SereneWomanEnglish_ConfidentWomanEnglish_PatientManEnglish_ComedianEnglish_BossyLeaderEnglish_Strong-WilledBoyEnglish_StressedLadyEnglish_AssertiveQueenEnglish_AnimeCharacterEnglish_JovialmanEnglish_WhimsicalGirlEnglish_Kind-heartedGirl
API

Avvio rapido

Imposta OPENROUTER_API_KEY localmente. Python richiede requests; JavaScript viene eseguito in Node.js. Conserva la chiave sul server.

Scegli una voce supportata. Sostituisci YOUR_VOICE_ID se non sono elencate voci.

Documentazione API

curl --fail-with-body https://openrouter.ai/api/v1/audio/speech \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"minimax/speech-2.8-turbo","input":"Hello!","voice":"English_expressive_narrator","response_format":"mp3"}' \
  --output speech.mp3
Capacità e modalità

Input → Output

Input
text
Output
speech
API

Parametri API supportati

Provider disponibili

1 Provider

Verificato: 16 settembre 2026

Provider live su OpenRouter

Disponibilità, latenza, throughput e routing cambiano continuamente. Consulta la fonte per i dati correnti.

OpenRouter

Minimax

Non indicato
Contesto
Non indicato
Output massimo
Non indicato
minimax

4 modelli

Tutti i modelli
minimax logominimax

MiniMax: H3 Max

MiniMax H3 Max is a video-generation model from MiniMax, jointly released with fal.ai. Derived through additional training from MiniMax H3, it is designed for faster text-to-video and image-to-video generation with...

Contesto
Non indicato
Input
text · image
Output
video
Output video: $0.08 al secondo
Vedi i dettagli del modello →
minimax logominimax

MiniMax: H3

MiniMax H3 is a lightweight, open-weights video generation model from MiniMax. It is designed for precise multimodal editing and controlled content generation, including instruction-guided edits, text and brand rendering, and...

Contesto
Non indicato
Input
text · image · video · audio
Output
video
Output video: $0.13 al secondoReference Image (first 5 free): $0.04 per immagine
Vedi i dettagli del modello →
minimax logominimax

MiniMax: Speech 2.8 HD

MiniMax Speech 2.8 HD is a text-to-speech model from MiniMax. It is suited for applications that generate spoken audio from text and accepts arbitrary MiniMax voice IDs.

Contesto
Non indicato
Input
text
Output
speech
Caratteri: $100 per milione di caratteri
Vedi i dettagli del modello →
minimax logominimax

MiniMax: MiniMax M3

MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agentic work, coding,...

Contesto
1.0M
Input
text · image · video
Output
text
Input: $0.3Output: $1.2per milione di token
Vedi i dettagli del modello →