Migrating off Simba 1.6

simba-english and simba-multilingual — the Simba 1.6 pair — are being withdrawn. This page is the one-stop migration guide: what changes, which model to move to, and how to buy time if you need it. The decision and the two dates were announced in the changelog entry that kicked this off.

What is changing

Withdrawal is two dated steps, both published up front:

2026-11-21 is the date that matters: it is a hard shutdown, not a version boundary you can sit below. Pinning buys time up to it, never past it.

Are you affected?

You are affected if a synthesis request sends model: "simba-english" or model: "simba-multilingual" to POST /v1/audio/speech or either /v1/audio/stream route.

You are not affected if you name simba-3.0 or simba-3.2, or omit model entirely — an omitted model resolves to simba-3.0, which is unchanged.

Where to go

For most integrations this is a one-line change — swap the model string and keep everything else — but check two things first:

• Voices on simba-3.2. Unlike every other model, simba-3.2 serves a curated voice set plus cloned voices Speechify has manually approved, not the full catalog. If the voice you use with simba-english isn’t one simba-3.2 accepts, the request is rejected — move that integration to simba-3.0 instead (it takes every built-in and cloned voice with no approval step).
• Omitting language. On simba-multilingual, leaving language out auto-detects the language from your input text. simba-3.0 instead falls back to the voice’s own locale. If you rely on detection, set language explicitly on the request when you move.

1
{
2
  "input": "Hello from Speechify.",
3
  "voice_id": "your-voice-id",
4
  "model": "simba-3.2"
5
}

1
curl -X POST https://api.speechify.ai/v1/audio/speech \
2
     -H "Authorization: Bearer <token>" \
3
     -H "Content-Type: application/json" \
4
     -d '{
5
  "input": "Hello! This is the Speechify text-to-speech API.",
6
  "voice_id": "geffen_32",
7
  "audio_format": "mp3",
8
  "model": "simba-3.2"
9
}'

Check your languages first

Most workspaces on simba-multilingual synthesize only English, German, Spanish, French, Italian or Brazilian Portuguese — all covered by simba-3.0. If that is you, simba-3.0 covers it today — set language explicitly on the request (see the note above on omitting it) and the switch is a one-liner.

If you synthesize outside that set, broader multilingual coverage is landing on the current model generation before the shutdown. If it is not in your hands by 2026-11-21 we move the date rather than cut the languages off — but talk to us so we can line your migration up with it rather than leave it to the deadline.

Buy time by pinning your API version

Not ready to change the model string yet? Pin your workspace’s API version to a date before 2026-09-21 and both models keep working, with no code change, until the 2026-11-21 sunset — see API Versioning for how to read and set Speechify-Version.

It is a migration window, not an exemption: the shutdown lands on 2026-11-21 whatever you pin.

Migration checklist

See also

• Simba 1.6 retirement changelog — the announcement and the two dates
• Models — the model catalog and the GET /v1/audio/models fields
• Language support — what simba-3.0 covers
• API Versioning — reading and pinning Speechify-Version