Audio

ElevenLabs Speech to Text (Scribe v2)

Credit-based pricing.

Try ElevenLabs Speech to Text (Scribe v2) →Compare models

ElevenLabs Speech to Text (Scribe v2) preview

Output

audio

Inputs

Reference audio (required)

LLM-ready

API & LLM schema

Exact request contract for this model. Agents can fetch it from /api/v1/models?id=fal-ai/elevenlabs/speech-to-text.

POST/api/v1/generate11 fields · 2 required

Field	Type	Requirement	Contract
`model_id`	constant	Required	ArtEmotion model identifier.
`extra`	object	Optional	Model-specific settings may also be nested here.
`max_credits`	number	Optional	Reject before submission if the estimated list price exceeds this cap. · Range: 1–…
`webhook_url`	string	Optional	Format: uri
`webhook_secret`	string	Optional	Optional model input.
`folder_id`	string	Optional	Optional model input.
`language_code`	string	Optional	Language of the audio. Auto-detect works well for most clips. · Allowed: , eng, spa, fra, deu, por, ita, hin, zho, jpn, kor, ara, rus, ind, nld, tur, pol, swe, fil, msa, ron, ukr, ell, ces, dan, fin, bul, hrv, slk, tam, vie, tha, heb, hun, nor, cat · Default:
`diarize`	boolean	Optional	Annotate which speaker is talking at each point. · Default: true
`tag_audio_events`	boolean	Optional	Tag non-speech sounds like laughter, applause, or music. · Default: true
`audio_url`	string	Required	Format: uri
`duration`	number	Optional	Estimate-only fallback when no media is supplied. Generation measures source bytes before reserving credits; client duration cannot lower the bill. · Default: 60 · Range: 1–7200

Minimal request example

{
  "model_id": "fal-ai/elevenlabs/speech-to-text",
  "audio_url": "https://example.com/audio"
}

Raw JSON Schema

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://www.artemotion.ai/api/v1/models?id=fal-ai%2Felevenlabs%2Fspeech-to-text",
  "title": "ElevenLabs Speech to Text (Scribe v2) generation request",
  "description": "Request body accepted by POST /api/v1/generate for fal-ai/elevenlabs/speech-to-text.",
  "type": "object",
  "properties": {
    "model_id": {
      "type": "string",
      "const": "fal-ai/elevenlabs/speech-to-text",
      "description": "ArtEmotion model identifier."
    },
    "extra": {
      "type": "object",
      "additionalProperties": true,
      "description": "Model-specific settings may also be nested here."
    },
    "max_credits": {
      "type": "number",
      "minimum": 1,
      "description": "Reject before submission if the estimated list price exceeds this cap."
    },
    "webhook_url": {
      "type": "string",
      "format": "uri",
      "maxLength": 2048
    },
    "webhook_secret": {
      "type": "string",
      "maxLength": 512
    },
    "folder_id": {
      "type": "string"
    },
    "language_code": {
      "title": "Language",
      "description": "Language of the audio. Auto-detect works well for most clips.",
      "default": "",
      "type": "string",
      "enum": [
        "",
        "eng",
        "spa",
        "fra",
        "deu",
        "por",
        "ita",
        "hin",
        "zho",
        "jpn",
        "kor",
        "ara",
        "rus",
        "ind",
        "nld",
        "tur",
        "pol",
        "swe",
        "fil",
        "msa",
        "ron",
        "ukr",
        "ell",
        "ces",
        "dan",
        "fin",
        "bul",
        "hrv",
        "slk",
        "tam",
        "vie",
        "tha",
        "heb",
        "hun",
        "nor",
        "cat"
      ]
    },
    "diarize": {
      "title": "Diarize",
      "description": "Annotate which speaker is talking at each point.",
      "default": true,
      "type": "boolean"
    },
    "tag_audio_events": {
      "title": "Tag Audio Events",
      "description": "Tag non-speech sounds like laughter, applause, or music.",
      "default": true,
      "type": "boolean"
    },
    "audio_url": {
      "type": "string",
      "format": "uri"
    },
    "duration": {
      "type": "number",
      "minimum": 1,
      "maximum": 7200,
      "default": 60,
      "description": "Estimate-only fallback when no media is supplied. Generation measures source bytes before reserving credits; client duration cannot lower the bill."
    }
  },
  "required": [
    "model_id",
    "audio_url"
  ],
  "additionalProperties": false
}

Browse schemas for every ArtEmotion model →

FAQ

How much does ElevenLabs Speech to Text (Scribe v2) cost on ArtEmotion?

Credit-based pricing. You pay in ArtEmotion credits — every plan and top-up converts USD to credits at a fixed rate.

Do I get my credits back if ElevenLabs Speech to Text (Scribe v2) fails?

Yes — failed generations are never charged. The credits are released back to your balance automatically.

Can I call ElevenLabs Speech to Text (Scribe v2) from the API?

Yes. Use POST /api/v1/generate with model_id: "fal-ai/elevenlabs/speech-to-text". See the API reference for the full schema.

Where are my generations stored?

Every output is saved to your personal Library. You can export or delete everything any time from Privacy & deletion.

Ready to generate with ElevenLabs Speech to Text (Scribe v2)?

Start now →

No commitment. New accounts get 50 free credits on signup. See pricing.