{"schema":"postcutoff/model@1","as_of":"2026-11-13T13:49:00+01:00","url":"https://postcutoff.com/m/elevenlabs-v4/","md":"https://postcutoff.com/m/elevenlabs-v4/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":"elevenlabs-v4","name":"Eleven v4 / Eleven v4 Turbo","org":"ElevenLabs","family":"Eleven v4","released":"2026-09-28","status":"current","type":"audio/speech","modality_in":["text"],"modality_out":["audio"],"open_weights":false,"model_license":"proprietary","context_window":null,"max_output":null,"knowledge_cutoff":null,"pricing":{"per_1k_characters":0.08,"unit":"per 1K characters, list price for eleven_v4 (eleven_v4_turbo $0.04/1K). The 72% launch promo ($0.022 / $0.011 per 1K) ended on 2026-10-12; the pricing page showed list prices with no discount label when checked on 2026-10-14","turbo_per_1k_characters":0.04,"promo_ended":"2026-10-12","source":"https://elevenlabs.io/pricing/api"},"price_line":"$0.08 per 1K characters","access":[{"provider":"ElevenLabs API","model_id":"eleven_v4","endpoint":"https://api.elevenlabs.io/v1/text-to-speech/{voice_id}","docs":"https://elevenlabs.io/docs/overview/capabilities/text-to-speech/eleven-v4"},{"provider":"ElevenLabs API","model_id":"eleven_v4_turbo","endpoint":"https://api.elevenlabs.io/v1/text-to-speech/{voice_id}","docs":"https://elevenlabs.io/docs/models"},{"provider":"fal","model_id":"elevenlabs/tts/eleven-v4","docs":"https://fal.ai/models/elevenlabs/tts/eleven-v4"},{"provider":"fal","model_id":"elevenlabs/tts/eleven-v4-turbo","docs":"https://fal.ai/models/elevenlabs/tts/eleven-v4-turbo"},{"provider":"Web app (ElevenCreative)","url":"https://elevenlabs.io/app"},{"provider":"Landing page / demos","url":"https://elevenlabs.io/v4"}],"capabilities":[{"name":"Context-aware \"performed\" delivery (new architecture)","detail":"Entirely new TTS architecture that 'reads a script the way a voice actor would', interpreting tone, pacing, emotion, character and context; preferred by ~75% of listeners (65-81% range) in blind head-to-head tests vs Cartesia Sonic 3.6, Inworld TTS-2, Gemini TTS, xAI TTS and GPT-4o mini TTS.","first":false,"discovered":"launch","source":"https://elevenlabs.io/blog/eleven-v4"},{"name":"#1 on Artificial Analysis TTS arena","detail":"Took #1 on the Artificial Analysis Provider Voice TTS Arena (Elo ~1315-1319 at launch, ahead of Cartesia Sonic 3.6 at 1275 and Gemini 3.8 Flash TTS at 1267) and #1 on AA's Pronunciation Robustness benchmark, #2 on Controlled Voice.","first":false,"discovered":"launch","source":"https://artificialanalysis.ai/text-to-speech/leaderboard"},{"name":"Real-time Turbo variant (~100 ms)","detail":"eleven_v4_turbo: ~100 ms median inference latency, ~150 ms median time to first speech (vs Cartesia Sonic 3.6 262 ms, GPT-4o mini TTS 814 ms per ElevenLabs), for voice agents.","first":false,"discovered":"launch","source":"https://elevenlabs.io/v4"},{"name":"Cross-lingual native accent, 90+ languages","detail":"90+ languages (new: Cantonese, Mongolian, Odia); when target language differs from the reference voice, v4 speaks with a fluent native accent instead of carrying over the source accent.","first":false,"discovered":"launch","source":"https://elevenlabs.io/docs/overview/capabilities/text-to-speech/eleven-v4"},{"name":"Inline tags incl. sound effects and free-text direction","detail":"Inline tags direct delivery, emotion, pacing, reactions, SFX and style, e.g. [laughs], [said angrily in French accent], [light rain], [phone buzzing], [quick, light, playful pace].","first":false,"discovered":"launch","source":"https://elevenlabs.io/blog/eleven-v4"},{"name":"Voice cloning from 10 s, PVC support restored","detail":"Instant Voice Clones from ~10 s of audio (docs still recommend 1-2 min); Professional Voice Clones supported again (not available on v3); speaker identity kept across regenerations/long-form.","first":false,"discovered":"launch","source":"https://elevenlabs.io/v4"},{"name":"IPA pronunciation control","detail":"Pronunciation control with IPA support; more natural multi-speaker dialogue.","first":false,"discovered":"launch","source":"https://www.youtube.com/watch?v=th_tXR2QQ6U"}],"entry":"2026-09-28-elevenlabs-eleven-v4","notes":"Launched 2026-09-28 (blog, YouTube 07:01 PT, X) in ElevenAgents, ElevenCreative and ElevenAPI, incl. free tier. eleven_v4: 10,000 chars/request; eleven_v4_turbo: no char limit listed on models page. Output formats MP3, WAV/PCM, u-law. Limitations: no Style/Speed sliders, no SSML (Stability + Similarity only); Voice Design voices may perform worse than with earlier models. Launch promo also: v4 free for Creator+ plans in ElevenCreative up to 2x monthly credits for two weeks. Third-party: on fal since launch day (fal X post https://x.com/fal/status/2104630460542325071): elevenlabs/tts/eleven-v4 at $0.08/1K chars and elevenlabs/tts/eleven-v4-turbo at $0.04/1K chars, the ElevenLabs list prices (fal model pages, checked 2026-09-29). Research led by Piotr Dabkowski (per press).","verified":"2026-10-14","body_md":"ElevenLabs' newest, most expressive TTS (eleven_v4); eleven_v4_turbo for agents/real time. Successor to Eleven v3.\n\n```bash\ncurl -X POST \"https://api.elevenlabs.io/v1/text-to-speech/$VOICE_ID\" -H \"xi-api-key: $ELEVENLABS_API_KEY\" \\\n  -H \"Content-Type: application/json\" -d '{\"text\":\"[laughs] Well... I did not expect that!\",\"model_id\":\"eleven_v4\"}' -o out.mp3\n```\n\nLaunch videos: https://www.youtube.com/watch?v=th_tXR2QQ6U (ElevenLabs), https://www.youtube.com/watch?v=4QHFkK2MTcw (ElevenLabs Developers).\n\nSources: https://elevenlabs.io/blog/eleven-v4 , https://elevenlabs.io/v4 , https://elevenlabs.io/docs/models , https://elevenlabs.io/pricing/api , https://x.com/ElevenLabs/status/2104572127617994917 , https://x.com/ElevenLabs/status/2104572138347004161 , https://x.com/ArtificialAnlys/status/2104578736687653293\n\n## Changelog\n- 2026-10-14: launch promo ended; pricing page shows list prices $0.08 / $0.04 per 1K characters (checked elevenlabs.io/pricing/api)\n- 2026-09-29: added fal access rows (elevenlabs/tts/eleven-v4, eleven-v4-turbo) with prices from fal model pages","page_url":"https://postcutoff.com/m/elevenlabs-v4/","standing":{"kind":"speech and audio","newer_count":14,"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":"elevenlabs-v3-conversational","name":"Eleven v3 Conversational","org":"ElevenLabs","released":"2026-08-19","page_url":"https://postcutoff.com/m/elevenlabs-v3-conversational/"},"after":{"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/"},"weights":"closed","licence":"proprietary","licence_permissive":false,"summary":"Closed weights; access is hosted only."}}