{"schema":"postcutoff/model@1","as_of":"2026-11-13T13:49:00+01:00","url":"https://postcutoff.com/m/soniox-tts-v2/","md":"https://postcutoff.com/m/soniox-tts-v2/index.md","disclosure":{"written_by":"AI agents (Claude Opus 5.5 in Claude Code)","editor":"human editor","policy":"https://postcutoff.com/about/"},"license":null,"id":"soniox-tts-v2","name":"Soniox TTS v2","org":"Soniox","family":"Soniox TTS","released":"2026-08-10","status":"current","type":"audio/speech","modality_in":["text","audio"],"modality_out":["audio"],"open_weights":false,"model_license":"proprietary","context_window":null,"max_output":null,"knowledge_cutoff":null,"pricing":{"input":4,"output":21.5,"unit":"USD per 1M tokens (text in / audio out); ≈ $0.70 per hour of generated speech (1 hour ≈ 30,000 audio tokens)","source":"https://soniox.com/pricing"},"price_line":"$4 in, $21.50 out per 1M tokens","access":[{"provider":"Soniox API (real-time streaming, WebSocket)","model_id":"tts-rt-v2","docs":"https://soniox.com/text-to-speech"}],"capabilities":[{"name":"60+ languages in one model, mid-sentence switching","detail":"Single multilingual model with mixed-language text and mid-sentence language switching; Soniox claims 'hallucination-free' output (no invented or dropped words) and accurate reading of emails, phone numbers and IDs.","first":false,"discovered":"launch","source":"https://soniox.com/blog/soniox-text-to-speech"},{"name":"Audio tags and 20-second voice cloning (v2)","detail":"TTS v2 adds expressive audio tags (whispering, laughter, hesitation, excitement), voice cloning from ~20 s of reference audio, and character-level timestamps.","first":false,"discovered":"launch","source":"https://audioxpress.com/news/soniox-tts-v2-adds-expressive-control-and-voice-cloning-to-its-multilingual-voice-ai-platform"}],"entry":null,"notes":"Soniox launched TTS on 2026-04-23 (tts-rt-v1); TTS v2 (tts-rt-v2, replacing v1) was reported by audioXpress on 2026-08-10. Streaming only; regions US, EU, Japan. The v2 date is from secondary press, not a Soniox post.","verified":"2026-09-29","body_md":"Soniox's text-to-speech, the companion to its [v5 STT](soniox-stt-v5.md), aimed at multilingual voice agents.\n\nSources: https://soniox.com/blog/soniox-text-to-speech , https://soniox.com/pricing , https://audioxpress.com/news/soniox-tts-v2-adds-expressive-control-and-voice-cloning-to-its-multilingual-voice-ai-platform","page_url":"https://postcutoff.com/m/soniox-tts-v2/","standing":{"kind":"speech and audio","newer_count":36,"newer":[{"id":"nemotron-3-5-transcribe","name":"NVIDIA Nemotron 3.5 Transcribe (30B-A4B)","org":"NVIDIA","released":"2026-10-28","page_url":"https://postcutoff.com/m/nemotron-3-5-transcribe/"},{"id":"hy-simulmt-30b-a3b","name":"Hy-SimulMT-30B-A3B","org":"Tencent","released":"2026-10-22","page_url":"https://postcutoff.com/m/hy-simulmt-30b-a3b/"},{"id":"eleven-realtime-v1-max","name":"Eleven Realtime v1 Max / Mini","org":"ElevenLabs","released":"2026-10-20","page_url":"https://postcutoff.com/m/eleven-realtime-v1-max/"},{"id":"voxtral-mini-transcribe-3","name":"Voxtral Mini Transcribe 3 (+ Mini Transcribe Realtime 3)","org":"Mistral AI","released":"2026-10-20","page_url":"https://postcutoff.com/m/voxtral-mini-transcribe-3/"},{"id":"voxtral-small-transcribe-3","name":"Voxtral Small Transcribe 3","org":"Mistral AI","released":"2026-10-20","page_url":"https://postcutoff.com/m/voxtral-small-transcribe-3/"}],"before":{"id":"soniox-stt-v5","name":"Soniox v5 (Async and Real-Time STT)","org":"Soniox","released":"2026-06-11","page_url":"https://postcutoff.com/m/soniox-stt-v5/"},"after":null,"weights":"closed","licence":"proprietary","licence_permissive":false,"summary":"Closed weights; access is hosted only."}}