MiniMax Speech 2.8 HD: the studio-quality tier of MiniMax's multilingual speech, same system voice library. Served via OpenRouter.

MiniMax Speech 2.8 Turbo: fast multilingual speech with MiniMax's system voice library. Served via OpenRouter.

Canopy Labs' Orpheus 3B: Llama-based open TTS with seven emotive English voices. Served via OpenRouter.

Sesame CSM-1B: the open conversational speech model behind Sesame's voice companions, with conversational and read-speech presets. Served via OpenRouter.

Fish Audio S2 Pro: expressive multilingual speech with a natural default voice. Served via OpenRouter.

Alibaba's Qwen Audio 3.0 TTS Plus: the higher-quality tier of Qwen's bilingual speech synthesis. Served via OpenRouter.

Alibaba's Qwen Audio 3.0 TTS Flash: fast bilingual (Chinese/English) speech synthesis. Served via OpenRouter.

Kokoro-82M: the tiny open-weight TTS model with 54 voices (American/British English, Spanish, French, Hindi, Italian, Japanese, Portuguese, Chinese) at a fract…

Deepgram Aura-2: 90 natural voices across English, Spanish, French, German, Italian, Dutch, Japanese and more, tuned for real-time narration. Served via OpenRo…

Mistral's Voxtral Mini TTS: 30 voice presets that combine a speaker with an emotion (neutral, happy, sad, excited, angry…) in English, British English and Fren…

Microsoft MAI-Voice-2 Flash: the faster, cheaper tier of MAI-Voice-2 with the same four multilingual voices. Served via OpenRouter.

Microsoft MAI-Voice-2: high-fidelity multilingual text-to-speech (EN, ES, FR, DE voices). Served via OpenRouter.

xAI's Grok Voice text-to-speech: five expressive English voices (Eve, Ara, Rex, Sal, Leo). Served via OpenRouter, billed per 1k characters.

Generate full-length songs or instrumentals from a text prompt, with optional auto-generated lyrics

Generate full-length songs up to 3 minutes from text prompts or images with Lyria 3 Pro, Google's most capable music generation model

Generate 30-second music clips from text prompts or images with Lyria 3, Google's music generation model

ElevenLabs Music is a cutting-edge AI music generation platform that creates professional-quality, royalty-free music tracks from simple text descriptions. Thi…

ACE-Step Audio is an advanced AI music generator that transforms text prompts into professional-quality audio tracks. This text-to-music AI model excels at cre…

AI music remixer with chord-aware controls for customizing generated tracks—remix, rearrange, and fine-tune AI music with harmonic precision

Bark by Suno AI is a revolutionary multilingual text-to-speech model capable of generating highly realistic speech, music, and sound effects across 100+ langua…

ElevenLabs Text-to-Speech (TTS) is the industry-leading AI voice synthesis platform delivering human-like speech in 29+ languages with exceptional naturalness …

Stability AI's music and sound generator from text or audio prompts—create professional audio tracks, ambiences, and soundscapes for creative projects

MusicGen by Meta AI is a sophisticated music generation model that creates high-quality, original music tracks from text descriptions or audio references. This…