Speechify launches Simba 3.5: one streaming-native TTS model across 48 languages
baseten · x · 2026-10-22
- Speechify released Simba 3.5, a single speech model covering 48 languages, streaming-native and compatible with every voice including cloned ones, aimed at speaking "like a local" across languages.
- Inference is powered by Baseten, which announced the partnership while congratulating the Speechify team.
More from Multimodal
- Prompt template: 'Abstract Symbolist Reverberation' for moody oil-paint AI art — LudovicCreator · 2026-10-22
- Kokon 0.10 reuses Qwen-Image 2.1's text encoder to write prompts, runs on 8GB cards — Ok-Director4174 · 2026-10-22
- Training-free 20B model Viveki generates real-time video heatmaps under 150ms — not-ekalabya · 2026-10-22
- Designer Khyati Trehan uses Gemini 4 Argon 3D for personal illustration work — alexanderchen · 2026-10-22
- Full 3:26 music video generated locally on a single AMD RX 7800 XT with open-source tools — wilppuse · 2026-10-22
- Fictional Lumea Serum ad shows how convincing AI-generated commercials have become — Amaan3024 · 2026-10-22