Models

Available models

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

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-english",
5
      "name": "Simba English",
6
      "default": true,
7
      "recommended": false,
8
      "description": "English-only synthesis; the model used when a request omits `model`.",
9
      "languages": [
10
        "en"
11
      ]
12
    },
13
    {
14
      "id": "simba-3.2",
15
      "name": "Simba 3.2",
16
      "default": false,
17
      "recommended": true,
18
      "description": "Streaming-native model with the lowest time-to-first-byte and richest expressivity, English only today.",
19
      "languages": [
20
        "en"
21
      ]
22
    }
23
  ]
24
}

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 stays stable for backwards compatibility), and the languages it can synthesize (BCP-47 locale strings matching the language parameter). 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 voice set: beatrice_32, dominic_32, edmund_32, geffen_32, harper_32, hugh_32, imogen_32, wyatt_32
• Currently English only; non-English voices return 400 until multilingual support ships
• Multilingual support coming soon
• Voice cloning is supported; each cloned voice currently requires manual Speechify review and approval of the voice key before it can be used on this model — see Voice Cloning

Simba 3.0

Earlier streaming-native model, still available for backwards compatibility.

• Prefer simba-3.2 for the latest quality
• Same curated voice-set behavior as simba-3.2
• Full support for SSML and emotion control
• Currently English only; non-English voices return 400

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

The current API default when model is omitted, and the model to use when your voice_id is a cloned/personal voice — those are not registered under the Simba 3 voice allow-list.

• 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

Voice cloning

Simba English and Simba Multilingual support two tiers of voice cloning; Simba 3.2 supports zero-shot voice cloning gated on manual Speechify approval of each voice key; Simba 3.0 serves a curated voice set only and does not accept cloned/personal voices:

See Voice Cloning for implementation details.

FAQ