Research-only speech models
18 in the catalogue today. Every one with what it costs, who sells it and where it stands.
Models that read text aloud. They are usually priced per character, which makes the arithmetic simple: a thousand characters is roughly a paragraph. The real choices are the voice itself, whether you may clone one, how much control you have over emotion and pacing, and latency — a model that sounds wonderful in a rendered file may be too slow to hold a conversation.
Weights published for research and explicitly not for selling. They are here because they exist, are often excellent, and are worth knowing about — and because the cheapest way to learn this is not after you have shipped. If a model on this list is what you want, the maker will usually license it commercially on request; that is a conversation, not a download.
- ChatTTS2Noise
- F5-TTSSWivid
- F5-TTS_RUSSIANMisha24-10
- Llama-OuteTTS-1.0-1BOuteAI
- Llasa-3BHKUST Audio
- MaskGCTamphion
- MiraTTSYatharthS
- OuteTTS-0.2-500MOuteAI
- VoiceCraftpyp1
- Voxtral-4B-TTS-2603Mistral AI
- fish-agent-v0.1-3bFish Audio
- fish-speech-1.2Fish Audio
- fish-speech-1.4Fish Audio
- fish-speech-1.5Fish Audio
- mms-ttsfacebook
- mms-tts-engfacebook
- s1-miniFish Audio
- seamless-streamingfacebook