Home / Servers / ElevenLabs API / speech_to_text
Speech To Text
An MCP tool from the ElevenLabs API server, hosted on mcp.hjlabs.in.
Speech To Text Transcribe an audio or video file. If webhook is set to true, the request will be processed asynchronously and results sent to configured webhooks. When use_multi_channel is true and the provided… [POST /v1/speech-to-text]
Name on the gateway: elevenlabs_api__speech_to_text · may change things.
Parameters
| Name | Type | Description |
|---|---|---|
token | string | A single-use authentication token created via POST… |
enable_logging | boolean | When enable_logging is set to false zero retention mode will be used for the… |
model_id required | string | The ID of the model to use for transcription. |
file | string | The file to transcribe (100ms minimum audio length). All major audio and video… |
language_code | string | An ISO-639-1 or ISO-639-3 language_code corresponding to the language of the… |
transcript_edit | string | Natural-language instruction applied to the final transcript (max 2000… |
tag_audio_events | boolean | Whether to tag audio events like (laughter), (footsteps), etc. in the… |
num_speakers | integer | The maximum amount of speakers talking in the uploaded file. Can help with… |
timestamps_granularity | none | word | character | The granularity of the timestamps in the transcription. 'word' provides… |
diarize | boolean | Whether to annotate which speaker is currently talking in the uploaded file. |
diarization_threshold | number | Diarization threshold to apply during speaker diarization. A higher value… |
additional_formats | array | A list of additional formats to export the transcript to. |
file_format | pcm_s16le_16 | other | The format of input audio. Options are 'pcm_s16le_16' or 'other' For… |
cloud_storage_url | string | [Deprecated] This parameter is deprecated and will be removed in the future.… |
source_url | string | The URL of an audio or video file to transcribe. Supports hosted video or… |
webhook | boolean | Whether to send the transcription result to configured speech-to-text… |
webhook_id | string | Optional specific webhook ID to send the transcription result to. Only valid… |
temperature | number | Controls the randomness of the transcription output. Accepts values between… |
seed | integer | If specified, our system will make a best effort to sample deterministically… |
use_multi_channel | boolean | Whether the audio file contains multiple channels where each channel contains… |
multichannel_output_style | separate | combined | Controls the response shape when use_multi_channel is enabled. 'separate'… |
webhook_metadata | string | Optional metadata to be included in the webhook response. This should be a… |
entity_detection | string | Detect entities in the transcript. Can be 'all' to detect all entities, a… |
no_verbatim | boolean | If true, the transcription will not have any filler words, false starts and… |
use_speaker_library | boolean | Whether to use the speaker library for identifying known speakers during… |
detect_speaker_roles | boolean | Whether to detect speaker roles (agent vs customer). Requires diarize=true.… |
entity_redaction | string | Redact entities from the transcript text. Accepts the same format as… |
entity_redaction_mode | string | How to format redacted entities. 'redacted' replaces with {REDACTED}… |
keyterms | array | A list of keyterms to bias the transcription towards. The keyterms are words… |
How to call it
Through the Smart Gateway, any client can run it by name with call_tool, or let the gateway find it with search_tools:
{
"name": "elevenlabs_api__speech_to_text",
"arguments": {
"model_id": "…"
}
}Or connect the ElevenLabs API server directly, which lists 487 tools including this one:
claude mcp add --transport http hj-elevenlabs-api https://mcp.hjlabs.in/mcp/elevenlabs-api \
--header "Authorization: Bearer YOUR_API_KEY"Try asking
Use the speech to text tool with token set to ….