Models

Available models

Pass the model ID as the model parameter in your API calls. If omitted, the API defaults to simba-3.0; we recommend explicitly setting model: "simba-3.2" on English-only integrations for the lowest TTFB and richest expressivity.

Simba 1.6 and your API version

simba-english and simba-multilingual - the Simba 1.6 pair - are being withdrawn in two steps:

If you use either model, you have until 2026-11-21 to migrate. Pinning your workspace’s API version to a date before 2026-09-21 keeps your integration working in the meantime, with no code change - see API Versioning for how to read and set it. It is a migration window, not an exemption: the shutdown lands on the same day whatever you pin.

New workspaces are pinned to the current version at signup, so a new integration cannot select the pair at all. Use simba-3.2 for English and simba-3.0 for the languages it covers.

Check which languages you actually send before you plan anything. Most workspaces on simba-multilingual synthesize only English, German, Spanish, French, Italian or Portuguese - all covered by simba-3.0, streaming-native and lower latency. If that is you, migrating is a one-line change.

If you do synthesize outside those seven, broader multilingual coverage is coming on the current model generation before the shutdown, and if it is not in your hands by then we move the date rather than cut the languages off. Talk to us so we can line your migration up with it.

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
}'

Listing models via the API

Fetch the current set of selectable models at runtime instead of hardcoding the table above. GET /v1/audio/models returns every model ID you can pass as the model parameter, marks the default (the model used when model is omitted) and the recommended model, and describes each one. Drive a model picker from this response so it stays current as models are added or the recommendation changes.

1
curl https://api.speechify.ai/v1/audio/models \
2
     -H "Authorization: Bearer <token>"

1
{
2
  "models": [
3
    {
4
      "id": "simba-3.0",
5
      "name": "Simba 3.0",
6
      "default": true,
7
      "recommended": false,
8
      "deprecated": false,
9
      "description": "Streaming-native model serving both English and multilingual synthesis under one id: English, German, Spanish, French, Italian and Portuguese, routed by the request `language`. The default when a request omits `model`.",
10
      "languages": [
11
        "en",
12
        "de-DE",
13
        "es-ES",
14
        "es-MX",
15
        "fr-FR",
16
        "it-IT",
17
        "pt-BR"
18
      ],
19
      "endpoints": [
20
        "/v1/audio/speech",
21
        "/v1/audio/stream",
22
        "/v1/audio/stream/with-timestamps"
23
      ],
24
      "curated_voices": false,
25
      "english_voices_only": false
26
    },
27
    {
28
      "id": "simba-3.2",
29
      "name": "Simba 3.2",
30
      "default": false,
31
      "recommended": true,
32
      "deprecated": false,
33
      "description": "Streaming-native model with the lowest time-to-first-byte and richest expressivity, English only today. Serves the curated voice roster, plus your workspace's own cloned voices where cloning has been enabled for it. Use `simba-3.0` for any other language.",
34
      "languages": [
35
        "en"
36
      ],
37
      "endpoints": [
38
        "/v1/audio/speech",
39
        "/v1/audio/stream",
40
        "/v1/audio/stream/with-timestamps"
41
      ],
42
      "curated_voices": true,
43
      "english_voices_only": true
44
    }
45
  ],
46
  "dialogue_models": [
47
    {
48
      "id": "simba-dialogue-1.0",
49
      "name": "Simba Dialogue 1.0",
50
      "default": true,
51
      "recommended": false,
52
      "deprecated": false,
53
      "description": "Multi-speaker model that renders a speaker-attributed script as one conversation with natural turn-taking.",
54
      "languages": [
55
        "en"
56
      ],
57
      "endpoints": [
58
        "/v1/audio/dialogue"
59
      ],
60
      "curated_voices": false,
61
      "english_voices_only": true
62
    }
63
  ]
64
}

Each entry carries the model id, a human-readable name and description, a default flag, a recommended flag (the model we suggest for new integrations, which is distinct from the default - the default accepts every voice, while the recommended model may serve a curated or English-only set), a deprecated flag, and the languages it can synthesize (BCP-47 locale strings matching the language parameter). deprecated marks a legacy model - a cue to de-emphasise it in a picker and steer new integrations elsewhere. A model being withdrawn carries two more fields: retired_at, the API version at which it stops being selectable (present only while your workspace is pinned below it, because at or after it the model is absent from this response entirely), and sunset_at, the date it is switched off for every version. Read them together - retired_at is what a pin defers, sunset_at is when that stops working. The list is always exactly what your workspace can call, so a picker driven off it never offers a model your synthesis request would reject. These values reflect current support and can change over time - a model may gain languages, for example - so read them at runtime rather than caching them: because the response shape is stable and clients ignore unknown fields, both changing values and future new fields are picked up without breaking existing integrations.

Voice cloning is not advertised per model here because whether cloned voices are available also depends on your plan; see Voice Cloning.

Simba 3.2

Streaming-native flagship model with the lowest TTFB (time to first byte) and richest expressivity. Recommended for new English integrations.

• Optimized for real-time streaming with the lowest startup latency
• Richer expressive range than earlier Simba generations
• Full support for SSML and emotion control
• Serves a curated stock voice set: beatrice_32, dominic_32, edmund_32, geffen_32, harper_32, hugh_32, imogen_32, wyatt_32
• English only; a non-English voice returns 400. Use simba-3.0 for the other supported languages
• Zero-shot voice cloning is supported: your workspace’s own cloned voices work here alongside the curated set — see Voice Cloning

Simba 3.0

Streaming-native model covering English plus six European languages. The model a request resolves to when it omits model.

• Officially supports en-*, de-DE, es-ES, es-MX, fr-FR, it-IT and pt-BR. See Language Support
• Set the language parameter to pick the language; when omitted, the voice’s own locale decides
• English and non-English are served by two separate trainings, but that routing is internal: the model ID you pass is always simba-3.0
• Languages outside the supported set often work but are not validated; simba-multilingual covers the full 30+ locale set on a pinned API version, until it is switched off on 2026-11-21
• Prefer simba-3.2 for English-only integrations; it has lower TTFB and richer expressivity
• Full support for SSML and emotion control
• Zero-shot voice cloning works self-serve, in every language the model supports - see Voice Cloning

Simba Multilingual

Supports multiple languages, including mixing languages within a single sentence.

• 35 locales covering 30 distinct languages live today
• Automatic language detection when the language parameter is omitted
• Zero-shot voice cloning works across all supported languages
• Fine-tuned voice cloning available (contact sales)

See Language Support for the full list.

Simba English

Kept for integrations that name it explicitly.

• Full support for SSML and emotion control
• Zero-shot voice cloning from short audio samples
• Fine-tuned voice cloning from hours of speaker audio (contact sales)
• Prefer simba-3.2 for new integrations using the built-in voice catalog; a new workspace cannot select this model at all

Voice cloning

Simba English and Simba Multilingual support two tiers of voice cloning; Simba 3.0 and Simba 3.2 both support zero-shot cloning self-serve:

A cloned voice works on simba-3.0 with no approval step, and on simba-english / simba-multilingual where your API version still offers them, until they are switched off on 2026-11-21. simba-3.2 cloning is enabled per workspace while it rolls out; once your workspace is enabled, every clone you own works there and you pass the voice ID exactly as you would a stock voice. Contact Speechify to be enabled.

See Voice Cloning for implementation details.

FAQ