8 articles in total
Alibaba Cloud CosyVoice v1 has been retired. Please migrate to same-price cosyvoice-v2, or more cost-effective cosyvoice-v3-flash. Most v1 voices map to v2 by appending the _v2 suffix.
Read MoreMiniMax releases the latest speech synthesis models speech-2.8-hd and speech-2.8-turbo, featuring all-new emotional tone tags for more expressive and engaging AI voices.
Read MoreWe've significantly increased the monthly credits for all subscription plans by 17%-31%, with no price change. Get more text-to-speech capacity at the same cost.
Read MoreElevenLabs' latest flagship model eleven_v3 is now available on UnifiedTTS, featuring support for 70+ languages, Audio Tags emotion control, multi-speaker dialogue, and more powerful features for a more natural and expressive voice synthesis experience.
Read MoreElevenLabs speech synthesis models now support the speed parameter, allowing speech rate adjustment from 0.7x to 1.2x for more flexible voice control.
Read MoreAlibaba Cloud CosyVoice third-generation models are now live! Introducing v3-flash and v3-plus with 31 high-quality Chinese voices, dialect support, improved performance, and more affordable pricing.
Read MoreWe've updated our supported TTS models, removing legacy versions and adding superior alternatives to make your choices simpler and more efficient.
Read MoreUnifiedTTS is now officially live - one API key to connect all major TTS service providers.
Read More