Sonic and Eleven v4 share 44 language codes on Sume
Sume's TTS Router lists the same 44 language codes for Sonic 3 and for Eleven v3 and v4, so the language field alone does not pick the engine.

On Sume the catalog lists 44 language codes for Sonic 3.x and the same 44 for Eleven v3 and v4, so the language field does not decide which engine to use. In tts-router-models.ts the Eleven v3 and v4 list is defined as the union of the Turbo v2.5 list (31 codes) and the Sonic 3 list (44 codes), which is exactly the Sonic list. A source comment says the real Eleven v3 and v4 families cover 70+ languages, and only the codes both families share are listed.
Counted from the repo on origin/main b28f3b0, read 2026-10-13.
| Row | Codes listed |
|---|---|
| Sonic 3.6, 3.5, 3, latest, preview | 44 |
| Sonic 2, Sonic Turbo | 15 (en, fr, de, es, pt, zh, ja, hi, it, ko, nl, pl, ru, sv, tr) |
| Eleven v3, v4, v4 Turbo | 44 (the union equals the Sonic 3 list) |
| Eleven Turbo v2.5 | 31 |
| Eleven Multilingual v2 | 28 |
So how do I pick?
Pick on what else you need: Sonic if you want timestamps, segmentation, avatar voices or WAV; Eleven if you need its voices or seed (v4 rows). Set language to the primary language of the script. A known mismatch with the voice's own language returns HTTP 409 tts_voice_language_mismatch; retry the same request and idempotency key with confirm_language_mismatch: true once you have checked it.
What about languages outside the list?
The catalog is the guard: the request is validated against it. If your language is not listed for the model you chose, pick a row that lists it, or generate the voice outside Sume and import the audio.
Sources
Related posts
More in Models
- AI video models with 4:3 and 3:4 on Sume: which rows list them
For 4:3 or 3:4 video on Sume, use a Seedance, Wan 3.0 or H3 row. Kling 3, Omni and Veo do not list those ratios. Read 2026-10-13.
- Veo 3.1 on Sume: Google Cloud rows, 720p, text-to-video only
Veo 3.1, Fast and Lite appear on Sume only where Google Cloud serves them: text-to-video, 720p, 4, 6 or 8 s, 16:9 or 9:16. Check your own list. Read 2026-10-13.
- WAND-Vega for e-commerce video: what Tencent says, what Sume lists
Tencent describes WAND-Vega as trained for vertical industries such as e-commerce. On Sume it is three text-to-video rows, 4-15 s, up to 4K. Read 2026-10-13.
- Which video_url row to call: Omni edit, Recast or Motion Transfer
Three Sume rows accept video_url: gemini-omni-flash-1.1 edits by prompt, h3-max-recast swaps people, higgsfield-genjutsu moves motion. Limits and prices.
Written by Sume