Open-weight speech models
69 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 under a licence that lets you run them where you like and sell what you build — Apache 2.0, MIT and their kin impose little beyond keeping the notice. This is the list to start from if you need the model on your own hardware, in your own region, or simply want no third party between you and it. The trade is that hosting is now your problem, and the prices shown beside each one are what somebody else charges to do it for you.
- AuKTencent Hunyuan
- Audio8-TTS-Preview-0.6bAudio8$0.000005per character1 selling
- Aura-1Deepgram
- Dia-1.6BNari Labs
- Dia2-2BNari Labs
- Fun-CosyVoice3-0.5B-2512QwenAudio
- GLM-TTSZ.ai
- GPT-SoVITSlj1995
- HeartMuLa-oss-3BHeartMuLa
- Index-TTSIndex Team
- IndicF5AI4Bharat
- Inflect-Micro-v2owensong
- Inflect-Nano-v1owensong
- Kimi-Audio-7B-InstructMoonshot AI
- KokoroHexgrad30th of 39$0.000001per character1 selling
- Kokoro-82M-v1.1-zhHexgrad
- LuxTTSYatharthS
- MOSS-TTSOpenMOSS-Team
- MOSS-TTS-Nano-100MOpenMOSS-Team
- MOSS-TTS-v1.5OpenMOSS-Team
- MegaTTS3ByteDance
- MeloTTS-EnglishMyShell.ai
- OpenVoiceMyShell.ai
- OpenVoiceV2MyShell.ai
- Orpheus 3BCanopy Labs$0.000007per character1 selling
- OuteTTS-0.1-350MOuteAI
- Qwen3-TTS-12Hz-0.6B-BaseAlibaba
- Qwen3-TTS-12Hz-0.6B-CustomVoiceAlibaba
- Qwen3-TTS-12Hz-1.7B-CustomVoiceAlibaba
- Qwen3-TTS-12Hz-1.7B-VoiceDesignAlibaba
- Soprano-1.1-80Mekwek
- Soprano-80Mekwek
- SoulX-Podcast-1.7BSoul-AILab
- SoulX-SingerSoul-AILab
- Step-Audio-TTS-3Bstepfun-ai
- VibeVoice-1.5BMicrosoft
- VibeVoice-7BVibeVoice Community (Unofficial)
- VibeVoice-Largeaoi-ot
- VibeVoice-Realtime-0.5BMicrosoft
- VoxCPM-0.5BOpenBMB
- VoxCPM1.5OpenBMB
- VoxCPM2OpenBMB
- WhisperSpeechWhisperSpeech
- Zonos-v0.1-hybridZyphra$0.000007per character1 selling
- Zonos-v0.1-transformerZyphra$0.000007per character1 selling
- Zonos2Zyphra
- acestep-v15-xl-turboACE-Step
- barkSuno
- bark-smallSuno
- chatterboxResembleAI29th of 39$0.00001per character1 selling
- chatterbox-turboResembleAI$0.000001per character1 selling
- csm-1bsesame$0.000007per character1 selling
- hertz-devStandard Intelligence
- indic-parler-ttsAI4Bharat
- kan-bayashi_ljspeech_vitsESPnet
- kugelaudio-0-openKugelaudio
- magenta-realtime-2Google
- metavoice-1B-v0.1MetaVoice
- mini-omnigpt-omni
- neutts-airNeuphonic
- orpheus-3b-0.1-pretrainedCanopy Labs
- parler-tts-large-v1Parler TTS
- parler-tts-mini-v1Parler TTS
- parler_tts_mini_v0.1Parler TTS
- resemble-enhanceResemble AI
- rvc-genshin-impactArkanDash
- speecht5_ttsMicrosoft
- tts-1.6b-en_frKyutai
- vuifluxions37th of 39