Modèles
Recherchez parmi les routes de modèles audio : TTS, STT, voix temps réel, clonage, doublage et utilitaires audio.
Type de modèleSélectionnez-en un ou plusieurs.
Parcourir toutes les pages de modèles
- models / amazon / amazon polly generative
- models / amazon / amazon polly long form
- models / amazon / amazon polly neural
- models / amazon / amazon polly standard
- models / amazon / amazon transcribe
- models / assemblyai / universal 2
- models / assemblyai / universal 3 5 pro
- models / assemblyai / universal 3 5 pro realtime
- models / assemblyai / universal streaming english
- models / assemblyai / universal streaming multilingual
- models / canopylabs / orpheus 3b
- models / canopylabs / orpheus arabic saudi
- models / canopylabs / orpheus v1 english
- models / cartesia / ink 2
- models / cartesia / ink whisper
- models / cartesia / sonic 3
- models / cartesia / sonic 3 5
- models / cartesia / sonic 3 6
- models / deepgram / aura
- models / deepgram / aura 2
- models / deepgram / flux
- models / deepgram / nova 3
- models / elevenlabs / eleven flash v2
- models / elevenlabs / eleven flash v2 5
- models / elevenlabs / eleven multilingual v2
- models / elevenlabs / eleven realtime v1 max
- models / elevenlabs / eleven realtime v1 mini
- models / elevenlabs / eleven turbo v2
- models / elevenlabs / eleven turbo v2 5
- models / elevenlabs / eleven v3
- models / elevenlabs / eleven v4
- models / elevenlabs / eleven v4 turbo
- models / elevenlabs / scribe v2
- models / elevenlabs / scribe v2 realtime
- models / fish / drama 3
- models / fish / s1
- models / fish / s2 1 pro
- models / fish / s2 pro
- models / fish / transcribe 1
- models / gemini / gemini 2 5 flash tts
- models / gemini / gemini 2 5 pro tts
- models / gemini / gemini 3 1 flash tts preview
- models / gemini / gemini 3 5 transcribe
- models / gemini / gemini 3 5 transcribe live
- models / gemini / gemini 3 8 flash lite tts
- models / gemini / gemini 3 8 flash tts
- models / gemini / gemini 3 8 live
- models / hexgrad / kokoro 82m
- models / inworld / inworld stt 1
- models / inworld / inworld tts 2
- models / inworld / inworld tts 2 flash
- models / minimax / speech 2 8 hd
- models / minimax / speech 2 8 turbo
- models / openai / gpt 4o mini transcribe
- models / openai / gpt 4o mini tts
- models / openai / gpt 4o transcribe
- models / openai / gpt 4o transcribe diarize
- models / openai / gpt live 1
- models / openai / gpt live transcribe
- models / openai / gpt realtime 2
- models / openai / gpt realtime 2 1
- models / openai / gpt realtime 2 1 mini
- models / openai / gpt realtime whisper
- models / openai / gpt transcribe
- models / openai / tts 1
- models / openai / tts 1 hd
- models / openai / whisper 1
- models / openai / whisper large v3
- models / openai / whisper large v3 turbo
- models / openai / whisper tiny en
- models / qwen / qwen3 asr 1 7b
- models / qwen / qwen3 asr flash
- models / qwen / qwen3 asr flash filetrans
- models / qwen / qwen3 asr flash realtime
- models / soniox / stt async v5
- models / soniox / stt rt v5
- models / soniox / tts rt v1
- models / soniox / tts rt v2
- models / sprag / chorus
- models / xai / grok stt
- models / xai / grok tts
- models / xai / grok voice 3 0