Fish Audio has launched Drama 3, a 35B parameter open-weight text-to-speech model that supports 83 languages and features a new mixture-of-experts architecture.
Suno has launched a new end-to-end audio model that generates speech and background music simultaneously as a single track.
Suno has introduced a beta version of its Speech feature, enabling users to generate spoken audio with synchronized background music.
Suno has launched a speech generation feature in public beta, allowing users to create voiceovers with optional background music via text prompts or custom scripts.
ElevenLabs has introduced its v4 speech model, featuring improved linguistic consistency, support for over 90 languages, and a high-speed Turbo variant for real-time voice agents.
Google has introduced Gemini 3.8 Flash TTS and Flash-Lite TTS, enabling prompt-based voice design and replication via API.
Google has launched Gemini 3.8 Flash TTS and Flash-Lite TTS, new AI models capable of voice cloning, multi-language speech synthesis, and granular emotional control.
Google has launched Gemini 3.8 Flash TTS and Flash-Lite TTS, enabling custom voice creation through text prompts and supporting over 100 languages with advanced audio control features.
Google has expanded its AI audio portfolio with the release of Gemini 3.8 text-to-speech models, aimed at enhancing multilingual voice generation for developers.
Modern speech synthesis tools offer high-quality voice generation, but achieving professional results requires careful text preparation and understanding of model-specific limitations.
ElevenLabs has released Dubbing v2, an AI model that translates speech by processing original audio to preserve vocal characteristics across more than 90 languages.
Yandex has launched an AI-powered Leo Tolstoy persona, allowing users to converse with the writer and influence his literary plots through the Alice AI platform.
