---
canonical_url: "https://docs.composio.dev/toolkits/allmodels"
markdown_url: "https://docs.composio.dev/toolkits/allmodels.md"
product: "platform"
version: null
last_updated: null
---

# AllModels

AllModels provides unified text-to-speech, speech-to-text, realtime voice, voice cloning, and account APIs across multiple AI providers.

- **Category:** audio & speech
- **Auth:** API_KEY
- **Composio-managed OAuth available?** N/A
- **Tools:** 40
- **Triggers:** 0
- **Slug:** `ALLMODELS`
- **Version:** 00000000_00

## Tools

### Add SDK Voice

**Slug:** `ALLMODELS_ADD_SDK_VOICE`

Clone one voice through the ElevenLabs voices.add compatibility endpoint. This mutation is the caller's attestation that the speaker consented and that the caller has rights to clone the uploaded recording. Creating the voice incurs a one-time provider cloning charge.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `name` | string | Yes | Voice name. AllModels slugifies it to a lower-case, organization-unique AM:@ identifier. |
| `files` | object | Yes | Exactly one audio sample from a speaker who consented to cloning. The ElevenLabs SDK models this as repeatable files parts, but AllModels refuses requests containing more than one sample. |
| `labels` | object | No | ElevenLabs SDK labels object. AllModels reads only the language value and ignores every other key. |
| `provider` | string | No | Optional AllModels cloning provider sent as x-allmodels-provider. Omit to let AllModels choose a provider compatible with the SDK inputs. |
| `description` | string | No | Optional free-form description of the cloned voice. |
| `remove_background_noise` | string | No | ElevenLabs compatibility value. AllModels accepts but ignores it because its cloning providers expose no background-noise removal option. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Create Custom Voice

**Slug:** `ALLMODELS_CREATE_CUSTOM_VOICE`

Clone a voice from an uploaded recording. This mutation attests that the speaker consented and that you have rights to use the sample. It may incur a one-time provider cloning fee; later speech generation is billed separately. The response can be pending: wait until both voice.status and providers[].status are active before generating speech.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `file` | object | Yes | Clean audio of one consenting speaker, without music or background noise. The sample and complete multipart request must meet the selected provider's size, duration, and format requirements. |
| `name` | string | Yes | Organization-unique voice name containing lower-case letters, digits, and hyphens. |
| `consent` | string | Yes | Required attestation that the speaker consented and that you have the rights to clone this recording. Must be the multipart string true. |
| `language` | string ("auto" | "ar" | "bg" | "bn" | "cs" | "da" | "de" | "el" | "en" | "es" | "fi" | "fr" | "gu" | "he" | "hi" | "hr" | "hu" | "id" | "it" | "ja" | "ka" | "kn" | "ko" | "ml" | "mr" | "ms" | "nl" | "no" | "or" | "pa" | "pl" | "pt" | "ro" | "ru" | "sk" | "sv" | "ta" | "te" | "th" | "tl" | "tr" | "uk" | "ur" | "vi" | "zh") | No | Sample language. Required for cartesia and inworld; omit for soniox, fish, minimax, and fal. Only inworld supports auto detection. |
| `provider` | string ("soniox" | "fish" | "minimax" | "cartesia" | "fal" | "inworld") | Yes | Cloning provider. Sample rules: soniox (up to 120 seconds), fish (unspecified duration), minimax (10-300 seconds), cartesia (at least 10 seconds), fal (at least 10 seconds), or inworld (3-30 seconds). Every provider accepts at most 10 MiB. |
| `consent_id` | string | No | Spoken-consent challenge ID only when the selected provider requires a separate challenge; otherwise omit it for the consent=true flow. |
| `description` | string | No | Optional description used to identify the cloned voice. |
| `capture_script_version` | string | No | Recording-script version label; omit when no versioned script was used. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Create Realtime Client Secret

**Slug:** `ALLMODELS_CREATE_REALTIME_CLIENT_SECRET`

Create a short-lived, single-use client secret and direct WebSocket URL from exactly one saved profile ID or complete inline profile. The returned secret and URL are ephemeral sensitive credentials and must not be logged or stored.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `profile` | string | No | Complete inline profile; provide exactly one of profile or profile_id. |
| `overrides` | object | No | Session-only profile overrides; the saved profile is not changed. |
| `profile_id` | string | No | Existing Realtime profile to use; provide exactly one of profile_id or profile. |
| `expires_in_seconds` | integer | No | How long the client may wait before opening the WebSocket, from 30 to 900 seconds. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Create Realtime Profile

**Slug:** `ALLMODELS_CREATE_REALTIME_PROFILE`

Create a reusable Realtime speech pipeline or direct speech-to-speech profile with model routing, audio, conversation, client, lifecycle, limits, and tags.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `profile` | string | Yes | Complete pipeline or speech-to-speech Realtime profile configuration. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Create Speech Engine

**Slug:** `ALLMODELS_CREATE_SPEECH_ENGINE`

Create a reusable Speech Engine that connects client audio to speech-to-text, an application WebSocket, and synthesized responses.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `config` | object | Yes | Complete ElevenLabs-compatible Speech Engine configuration. |
| `stt_extension` | object | No | AllModels STT model, provider, provider-specific options, and portable input settings. |
| `tts_extension` | object | No | AllModels TTS model, provider, provider-specific options, and portable input settings. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Create Speech Engine Signed URL

**Slug:** `ALLMODELS_CREATE_SPEECH_ENGINE_SIGNED_URL`

Create a short-lived, single-use WebSocket URL that lets one client connect to an existing Speech Engine without receiving the account API key. The returned URL contains an ephemeral credential and must be handled as a secret.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `agent_id` | string | Yes | Speech Engine identifier for which to issue a signed client URL. |
| `include_conversation_id` | string ("0" | "1" | "true" | "false") | No | Whether the response includes a conversation_id. Send exactly 1 or true to include it, or 0 or false to omit it. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Create Top-Up Link

**Slug:** `ALLMODELS_CREATE_TOP_UP_LINK`

Create an expiring payment checkout link for adding a specified USD amount to the connected AllModels account. This initiates a financial top-up workflow by creating an external payment link, but does not itself charge a payment method or add funds; payment must be completed outside this action.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `amount_usd` | number | Yes | USD amount to add to the account balance, from 5 to 1000. |
| `idempotency_key` | string | No | Identifier for safely retrying the same amount after a timeout or network error. Reuse it only when amount_usd is unchanged. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Delete Custom Voice

**Slug:** `ALLMODELS_DELETE_CUSTOM_VOICE`

Permanently delete an organization-owned cloned voice by voice_id. This destructive action cannot be undone, and deletion may take about a minute to finish.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `voice_id` | string | Yes | Complete AllModels voice ID returned by create or list. The selected custom voice will be permanently deleted. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Delete Realtime Profile

**Slug:** `ALLMODELS_DELETE_REALTIME_PROFILE`

Permanently delete a saved Realtime profile by profile_id. This destructive action cannot be undone.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `profile_id` | string | Yes | Realtime profile identifier to permanently delete. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Delete SDK Voice

**Slug:** `ALLMODELS_DELETE_SDK_VOICE`

Permanently delete an organization-owned cloned voice through the ElevenLabs voices.delete compatibility endpoint. This destructive action cannot be undone, and cached requests may keep using the voice for about one minute.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `voice_id` | string | Yes | AM:@ voice ID of the organization-owned cloned voice to permanently delete. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Delete Speech Engine

**Slug:** `ALLMODELS_DELETE_SPEECH_ENGINE`

Permanently delete a Speech Engine so it can no longer issue new signed conversation URLs. This destructive action cannot be undone.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `speech_engine_id` | string | Yes | Speech Engine identifier to permanently delete. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Download Custom Voice Sample

**Slug:** `ALLMODELS_DOWNLOAD_CUSTOM_VOICE_SAMPLE`

Download the audio sample authorized by a short-lived custom-voice cloning token.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `token` | string | Yes | Opaque single-clone grant issued by AllModels and valid for ten minutes. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Generate OpenAI Speech

**Slug:** `ALLMODELS_GENERATE_OPENAI_SPEECH`

Generate speech through AllModels' OpenAI-compatible endpoint. Returns a downloadable audio file by default or the complete SSE event stream when stream_format is sse. This consumes the connected account's prepaid balance.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `input` | string | Yes | Text to synthesize, limited to 4,096 characters. |
| `model` | string | Yes | TTS model ID, optionally prefixed with its provider ID. |
| `speed` | number | No | Playback-speed multiplier where the selected provider supports it. |
| `voice` | string | Yes | Voice ID string or an object containing the voice ID under id; cloned AllModels voices use IDs such as AM:@narrator. |
| `provider` | object | No | Body-level provider priority, allowlist, denylist, and fallback settings. |
| `instructions` | string | No | Delivery instructions such as tone, accent, pacing, or character. Unsupported instructions fail instead of being silently ignored. |
| `provider_only` | array | No | Only these provider IDs may serve the request, serialized as CSV. |
| `stream_format` | string ("audio" | "sse") | No | Return offloaded audio bytes or the complete OpenAI-compatible SSE stream. |
| `provider_order` | array | No | Provider IDs to try first, serialized as one comma-separated query value. |
| `allow_fallbacks` | boolean | No | Set false to prevent fallback to another provider. |
| `provider_ignore` | array | No | Provider IDs to exclude, serialized as CSV. |
| `response_format` | string ("mp3" | "opus" | "aac" | "flac" | "wav" | "pcm") | No | Requested audio format: mp3, opus, aac, flac, wav, or pcm. |
| `provider_options` | object | No | Body-level provider-specific TTS options. Documented and future option keys are forwarded unchanged. |
| `query_provider_options` | object | No | Provider-specific query options. Each entry is sent as provider_options[name]=value and overrides the equivalent direct option. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Generate SDK Speech

**Slug:** `ALLMODELS_GENERATE_SDK_SPEECH`

Generate a complete audio file through AllModels' ElevenLabs-compatible textToSpeech.convert endpoint. This consumes the connected account's prepaid balance.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `text` | string | Yes | Text to synthesize. |
| `model_id` | string | Yes | Model ID as a bare name or author/model slug; AllModels applies no default model. |
| `provider` | object | No | OpenRouter-style provider preferences. |
| `voice_id` | string | Yes | Voice ID, such as eve for Grok TTS or AM:@narrator for a cloned voice. |
| `instructions` | string | No | Delivery instructions such as tone, accent, pacing, or character. Unsupported instructions fail instead of being silently ignored. |
| `output_format` | string | No | Output format such as mp3_44100_128 or pcm_16000. |
| `provider_only` | array | No | Only these provider IDs may serve the request. |
| `enable_logging` | string | No | ElevenLabs-compatible logging control value. |
| `provider_order` | array | No | Provider IDs in preferred order, serialized as one comma-separated query value. |
| `voice_settings` | object | No | Voice settings supported by the selected provider. |
| `allow_fallbacks` | boolean | No | Set false to prevent fallback to another provider. |
| `provider_ignore` | array | No | Provider IDs that must not serve the request. |
| `provider_options` | object | No | Provider-specific text-to-speech options. |
| `generation_config` | object | No | ElevenLabs-only generation tuning; other providers ignore it. |
| `query_provider_options` | object | No | Provider-specific query options sent as provider_options[name]=value; bracketed values take precedence. |
| `optimize_streaming_latency` | string | No | ElevenLabs-compatible streaming latency optimization value. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Get Account Balance

**Slug:** `ALLMODELS_GET_ACCOUNT_BALANCE`

Return the connected account's paid and spendable credits, USD balance, availability state, and monthly-billing fields when present.

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Get Account Usage

**Slug:** `ALLMODELS_GET_ACCOUNT_USAGE`

Return daily API-key usage and aggregate request, credit, and USD cost totals for a range of at most 90 days, optionally filtered by provider, model, or capability. Recent usage may take a short time to appear.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `model` | string | No | Restrict usage to this model ID. |
| `to_time` | string | No | Inclusive RFC 3339 end time; defaults to the current time. The range from from_time through to_time may not exceed 90 days. |
| `provider` | string | No | Restrict usage to this provider ID. |
| `from_time` | string | No | Inclusive RFC 3339 start time; defaults to 30 days before to_time. |
| `capability` | string ("tts" | "stt" | "speech-to-speech" | "llm") | No | Restrict usage to this capability. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Get Custom Voice

**Slug:** `ALLMODELS_GET_CUSTOM_VOICE`

Return one organization-owned cloned voice, its readiness status, supported models, and provider status by voice_id.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `voice_id` | string | Yes | Complete AllModels voice ID returned by create or list. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Get OpenAI Credits

**Slug:** `ALLMODELS_GET_OPENAI_CREDITS`

Return available account funds in the OpenRouter-compatible credits envelope used by OpenAI-style clients. Use the account balance action for the detailed credit breakdown.

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Get Provider Skill

**Slug:** `ALLMODELS_GET_PROVIDER_SKILL`

Return the provider-specific Markdown guide for steering TTS delivery through AllModels.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `file` | string | Yes | Provider skill filename in <provider>.md form. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Get Realtime Profile

**Slug:** `ALLMODELS_GET_REALTIME_PROFILE`

Return one saved pipeline or speech-to-speech Realtime profile by its profile_id, including the complete nested configuration.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `profile_id` | string | Yes | Realtime profile identifier returned by create or list. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Get SDK Voice

**Slug:** `ALLMODELS_GET_SDK_VOICE`

Return one organization-owned cloned voice through the ElevenLabs voices.get compatibility endpoint.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `voice_id` | string | Yes | Complete AllModels AM:@ voice ID for an organization-owned cloned voice. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Get Speech Engine

**Slug:** `ALLMODELS_GET_SPEECH_ENGINE`

Return one Speech Engine configuration by its speech_engine_id.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `speech_engine_id` | string | Yes | Speech Engine identifier returned by create or list. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Check API Health

**Slug:** `ALLMODELS_HEALTH_CHECK`

Check whether the AllModels API and its LLM dependency are available, including nullable deployment commit identifiers.

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### List Account Activity

**Slug:** `ALLMODELS_LIST_ACCOUNT_ACTIVITY`

List individual API requests made with the connected API key, newest first, with time, provider, model, capability, and status filters plus an opaque continuation cursor.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `limit` | integer | No | Maximum activity records to return in this page, from 1 to 100. |
| `model` | string | No | Restrict activity to this model ID. |
| `cursor` | string | No | Opaque next_cursor from the previous page; omit for the first page. |
| `status` | string ("completed" | "failed") | No | Restrict activity to completed or failed requests. |
| `to_time` | string | No | Inclusive RFC 3339 end time; defaults to now. The range from from_time may not exceed 90 days. |
| `provider` | string | No | Restrict activity to this provider ID. |
| `from_time` | string | No | Inclusive RFC 3339 start time; defaults to 30 days before to_time. |
| `capability` | string ("tts" | "stt" | "speech-to-speech" | "llm") | No | Restrict activity to this model capability. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### List Account Transactions

**Slug:** `ALLMODELS_LIST_ACCOUNT_TRANSACTIONS`

List organization credit events such as top-ups, grants, refunds, adjustments, and expirations, returning one page and an opaque continuation cursor.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `limit` | integer | No | Maximum transactions to return in this page, from 1 to 100. |
| `cursor` | string | No | Opaque next_cursor from the previous page; omit for the first page. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### List Custom Voices

**Slug:** `ALLMODELS_LIST_CUSTOM_VOICES`

List the organization's cloned voices across projects, newest first by default, returning one cursor-controlled page.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `cursor` | string | No | Opaque next_cursor from the previous page; omit for the first page. |
| `page_size` | integer | No | Maximum cloned voices in this page, from 1 to 100. |
| `sort_direction` | string ("asc" | "desc") | No | Use desc for newest first or asc for oldest first. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### List Models

**Slug:** `ALLMODELS_LIST_MODELS`

List available TTS, STT, and speech-to-speech models with aliases, provider capabilities, endpoints, instruction support, and pricing.

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### List Providers

**Slug:** `ALLMODELS_LIST_PROVIDERS`

List providers keyed by provider ID with their default models and voices, supported TTS/STT models, formats, capabilities, and pricing.

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### List Realtime Profiles

**Slug:** `ALLMODELS_LIST_REALTIME_PROFILES`

List saved Realtime profiles with name search, sort direction, and one cursor-controlled page.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `cursor` | string | No | Opaque next_cursor from the previous page; omit for the first page. |
| `search` | string | No | Search saved Realtime profile names. |
| `page_size` | integer | No | Maximum profiles to return in this page, from 1 to 100. |
| `sort_direction` | string ("asc" | "desc") | No | Sort matching profiles in ascending or descending order. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### List SDK Voices

**Slug:** `ALLMODELS_LIST_SDK_VOICES`

List voices from one TTS provider in the ElevenLabs voices.get_all compatibility envelope.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `provider_only` | string ("deepgram" | "elevenlabs" | "soniox" | "fish" | "groq" | "grok" | "minimax" | "cartesia" | "together" | "openai" | "gemini" | "fal" | "inworld" | "amazon" | "sprag") | No | TTS provider whose voices to return. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### List Speech Engines

**Slug:** `ALLMODELS_LIST_SPEECH_ENGINES`

List permanent Speech Engines with name search, sort controls, and one cursor-controlled page.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `cursor` | string | No | Opaque next_cursor from the previous page; omit for the first page. |
| `search` | string | No | Search Speech Engine names. |
| `sort_by` | string | No | Speech Engine field to sort by. |
| `page_size` | integer | No | Maximum Speech Engines to return in this page, from 1 to 100. |
| `sort_direction` | string ("asc" | "desc") | No | Sort matching Speech Engines in ascending or descending order. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Search SDK Voices

**Slug:** `ALLMODELS_SEARCH_SDK_VOICES`

List voices for one text-to-speech provider in the ElevenLabs SDK search compatibility envelope, optionally limiting the single returned page.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `page_size` | integer | No | Maximum number of voices to return. The endpoint returns a single page. |
| `provider_only` | string ("deepgram" | "elevenlabs" | "soniox" | "fish" | "groq" | "grok" | "minimax" | "cartesia" | "together" | "openai" | "gemini" | "fal" | "inworld" | "amazon" | "sprag") | No | Return voices from this text-to-speech provider. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Search Voices

**Slug:** `ALLMODELS_SEARCH_VOICES`

Search the public voice catalogue by text, model, provider, language, category, labels, and sort order, returning one cursor-controlled page.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `sort` | string ("featured" | "relevance" | "newest" | "popular" | "name") | No | Sort order. Relevance requires search_query. |
| `cursor` | string | No | Opaque next_cursor from the previous page; omit for the first page. |
| `labels` | array | No | Facet filters such as gender:female; each value is sent as a repeated label query parameter. |
| `models` | array | No | AllModels model IDs to match; each value is sent as a repeated model query parameter. |
| `languages` | array | No | Language IDs such as en to match; each value is sent as a repeated language query parameter. |
| `page_size` | integer | No | Maximum voices in this page, from 1 to 100. |
| `providers` | array | No | Provider IDs to match; each value is sent as a repeated provider query parameter. |
| `categories` | array | No | Voice categories such as official or community to match; each value is sent as a repeated category query parameter. |
| `search_query` | string | No | Search voice names and descriptive metadata. |
| `include_facets` | string ("true" | "false") | No | Whether to include available filters and result counts. |
| `first_seen_after` | string | No | Return voices added after this RFC 3339 timestamp. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Start Agent Signup

**Slug:** `ALLMODELS_START_AGENT_SIGNUP`

Send a six-digit AllModels access code to an account owner's email address. This action requires a connected AllModels API key and has an external email side effect. After receiving the code, verify it with the same email address. The verification action returns a new or replacement key that must be used to create a new connection; it does not update the current connection. AllModels publishes no numeric request quota, but may return 429; wait for the Retry-After interval before requesting another code.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `email` | string | Yes | Email address whose owner will receive and approve the six-digit AllModels access code. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Stream SDK Speech

**Slug:** `ALLMODELS_STREAM_SDK_SPEECH`

Generate speech through the ElevenLabs-compatible streaming HTTP endpoint and return the produced audio as a downloadable file. This consumes the connected account's prepaid balance.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `text` | string | Yes | Text to synthesize, limited to 2,000 characters. |
| `model_id` | string | Yes | Required model ID as a bare name or provider-prefixed slug; the router applies no default model. |
| `provider` | object | No | Body-level provider priority, allowlist, denylist, and fallback settings. |
| `voice_id` | string | Yes | Voice ID to speak with, such as alloy, eve, or an AllModels cloned voice ID. |
| `instructions` | string | No | Delivery instructions such as tone, accent, pacing, or character. Unsupported instructions fail instead of being silently ignored. |
| `output_format` | string | No | Output token such as mp3_44100_128 or pcm_16000. |
| `provider_only` | array | No | Only these providers may serve the request, serialized as CSV. |
| `enable_logging` | string | No | ElevenLabs-compatible logging query option forwarded where supported. |
| `provider_order` | array | No | Providers to try first, serialized as one comma-separated query value. |
| `voice_settings` | object | No | Provider-supported voice controls, including speed and ElevenLabs settings. |
| `allow_fallbacks` | boolean | No | Set false to prevent fallback to another provider. |
| `provider_ignore` | array | No | Providers that must not serve the request, serialized as CSV. |
| `provider_options` | object | No | Body-level provider-specific TTS settings. Keys and nested values are forwarded unchanged to support every documented provider option. |
| `generation_config` | object | No | ElevenLabs generation tuning; other providers ignore this object. |
| `query_provider_options` | object | No | Provider-specific query options. Each entry is sent as provider_options[name]=value and takes precedence over an equivalent direct query option. |
| `optimize_streaming_latency` | string | No | ElevenLabs-compatible latency query option forwarded where supported. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Transcribe OpenAI Audio

**Slug:** `ALLMODELS_TRANSCRIBE_OPENAI_AUDIO`

Transcribe an uploaded audio file through AllModels' OpenAI-compatible endpoint and preserve JSON, text, subtitle, or SSE output. This consumes the connected account's prepaid balance.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `file` | object | Yes | WAV, MP3, FLAC, MP4/M4A, OGG, or WebM audio file to transcribe. |
| `model` | string | Yes | STT model ID, optionally provider-prefixed. |
| `prompt` | string | No | Text that guides the transcription style or vocabulary. |
| `stream` | boolean | No | Request an SSE transcript stream when the selected model supports it. |
| `include` | array | No | Additional documented response fields to include. |
| `language` | string | No | Expected language of the audio. |
| `provider` | object | No | AllModels provider-routing preferences, serialized as JSON in multipart form data. |
| `temperature` | number | No | Sampling temperature where supported by the model. |
| `provider_only` | array | No | Only these provider IDs may serve the request, sent as a comma-separated query parameter. |
| `provider_order` | array | No | Provider IDs to try first, sent as a comma-separated query parameter. |
| `allow_fallbacks` | boolean | No | Set false to prevent fallback to another provider. |
| `provider_ignore` | array | No | Provider IDs to exclude, sent as a comma-separated query parameter. |
| `response_format` | string ("json" | "text" | "srt" | "vtt" | "verbose_json" | "diarized_json") | No | Response representation: JSON, plain text, SRT, VTT, verbose JSON, or diarized JSON. |
| `provider_options` | object | No | Provider-specific STT options, serialized as JSON in multipart form data. |
| `chunking_strategy` | string | No | Provider-supported chunking strategy, such as auto or a strategy object. |
| `known_speaker_names` | array | No | Known speaker labels, in the same order as known_speaker_references. |
| `query_provider_options` | object | No | Provider-specific query options; these override equivalent direct options. |
| `timestamp_granularities` | array | No | Word and/or segment timestamps to include with verbose JSON. |
| `known_speaker_references` | array | No | Reference audio files or audio data URLs corresponding to known_speaker_names. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Transcribe SDK Audio

**Slug:** `ALLMODELS_TRANSCRIBE_SDK_AUDIO`

Transcribe an uploaded audio file through AllModels' ElevenLabs-compatible endpoint and return text, language, and available word or character timing. This consumes the connected account's prepaid balance.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `file` | object | Yes | WAV, MP3, FLAC, MP4/M4A, OGG, or WebM audio file to transcribe. |
| `diarize` | string | No | Set to true or 1 to enable speaker diarization. |
| `model_id` | string | Yes | Required STT model ID as a bare name or provider-prefixed slug. |
| `provider` | object | No | Provider priority, allowlist, denylist, and fallback settings. |
| `language_code` | string | No | Expected language code. |
| `provider_only` | array | No | Only these provider IDs may serve the request, sent as CSV. |
| `provider_order` | array | No | Provider IDs to try first, sent as CSV. |
| `allow_fallbacks` | boolean | No | Set false to prevent fallback to another provider. |
| `provider_ignore` | array | No | Provider IDs that must not serve the request, sent as CSV. |
| `provider_options` | string | No | Provider-specific transcription options matching one documented provider contract. |
| `query_provider_options` | object | No | Provider-specific query options sent as provider_options[name]=value; these take precedence over equivalent direct options. |
| `timestamps_granularity` | string ("none" | "word" | "character") | No | Timestamp detail to include in the response. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Update Realtime Profile

**Slug:** `ALLMODELS_UPDATE_REALTIME_PROFILE`

Patch selected fields of a saved pipeline or speech-to-speech Realtime profile. Omitted fields remain unchanged, explicit null values are retained, and a missing profile is not created.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `patch` | object | Yes | Sparse profile patch. Omitted fields remain unchanged; explicitly null fields are sent to the provider. |
| `profile_id` | string | Yes | Realtime profile identifier to update. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Update Speech Engine

**Slug:** `ALLMODELS_UPDATE_SPEECH_ENGINE`

Partially update an existing AllModels Speech Engine. Only explicitly supplied configuration fields are changed; use the STT and TTS extensions for non-ElevenLabs model routing or settings without a standard Speech Engine field.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `config` | object | Yes | Sparse Speech Engine patch. Only explicitly supplied fields are sent; omitted nested fields remain unchanged. |
| `stt_extension` | object | No | AllModels STT model, provider, provider options, and portable input settings. |
| `tts_extension` | object | No | AllModels TTS model, provider, provider options, and portable input settings. |
| `speech_engine_id` | string | Yes | Speech Engine identifier to update. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Verify Agent Signup

**Slug:** `ALLMODELS_VERIFY_AGENT_SIGNUP`

Verify an emailed six-digit AllModels signup code using the same email address that requested it. This action requires a connected AllModels API key. Success creates and returns a sensitive new or replacement API key in full only once; store it securely and use it to create a new connection because this action cannot update the current connection. Never log, cache, place the key in fixtures, or share it. If claimUrl is returned, give it only to the account owner so they can claim free credit in a browser; it does not sign them in. If the code expired or was already used, start the signup flow again.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `code` | string | Yes | Six-digit verification code sent to the email address. |
| `email` | string | Yes | The same email address used to request the AllModels verification code. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |
