GIZAI
k2-fsaOmniVoiceMassively multilingual zero-shot TTS with Voice Clone and Voice Design modes, prompt preprocessing, speed, duration, and diffusion controls.
ACE-StepACE-Step 1.5Music model for structured songs with style tags, lyrics, BPM, key, language, and long durations.
Stability AIStable Audio 3 MediumFast high-quality music and sound generation with audio-to-audio editing, inpainting, and continuation.
Owen SongInflect Micro v2Instant CPU-efficient English narration with one consistent synthetic male voice.
Inworld AIInworld TTS-1.5 MiniLow-latency expressive text-to-speech optimized for real-time apps
xAIxAI Text-to-SpeechExpressive text-to-speech with over two dozen voices, speech tags, and multilingual support
OpenAIOpenAI TTS (Text to Speech)Reliable OpenAI text-to-speech for clear narration, dialogue, and assistant voice output.
MiniMaxMiniMax Music 1.5Song model for natural vocals and rich arrangements with English or Chinese structured lyrics.
Fish AudioFish Audio S2.1 ProFlagship multilingual text-to-speech with natural language voice control and realtime streaming
Inworld AIInworld Realtime TTS-2Conversational text-to-speech with realtime voice direction and audio-aware delivery
GoogleGemini 3.1 Flash TTSExpressive text-to-speech with audio tags, multi-speaker dialogue, and 70+ languages
MiniMaxMiniMax Music 2.6Promptable full-song generation with vocals, lyrics, BPM and key control
MiniMaxMiniMax Music CoverAudio-to-audio song transformation that preserves melody while changing style
RunwareACE-Step v1.5 XL Base4B music generation model with higher audio quality and full editing task support
RunwareACE-Step v1.5 XL SFTHighest-quality 4B music generation model with CFG-controlled prompt adherence
RunwareACE-Step v1.5 XL TurboFast 4B music generation model with 8-step inference for higher-quality rapid iteration
MiniMaxMiniMax Speech 2.8High-quality text-to-speech with expressive, natural voice synthesis
Inworld AIInworld TTS-1.5 MaxHigh-fidelity expressive text-to-speech with rich prosody and multilingual support
AlibabaQwen3-TTS 1.7B BaseHigh-quality multilingual text-to-speech with voice cloning and ultra-low latency
AlibabaQwen3-TTS 1.7B CustomVoiceText-to-speech with preset premium timbres and precise style control
AlibabaQwen3-TTS 1.7B VoiceDesignText-to-speech with voice creation from natural language descriptions
RunwareACE-Step v1.5 BaseOpen-source music generation with voice cloning, lyric editing, and multilingual support
RunwareACE-Step v1.5 TurboFast music generation optimized for speed with reduced inference steps
RunwareDia2 2BStreaming dialogue TTS with voice cloning, non-verbal cues, and multi-speaker support