Mesh APIAudio

Create Transcription

View as Markdown
Transcribe an audio file to text. Provider is resolved automatically from the model name via model_pricing. `file` is optional for providers that accept `source_url` or `cloud_storage_url`. `additional_formats` is a JSON-encoded string (ElevenLabs-specific, ignored by others). Returns `{"text": "..."}` by default, or per-word structure (`words[]` with each token's `type`) when `response_format=verbose_json`.

Authentication

AuthorizationBearer

Bearer authentication of the form Bearer <token>, where token is your auth token.

Query parameters

enable_loggingbooleanOptionalDefaults to true

Request

This endpoint expects a multipart form containing an optional file.
modelstringRequired
filefileOptional
response_formatstring or nullOptional
language_codestring or nullOptional
tag_audio_eventsboolean or nullOptional
num_speakersinteger or nullOptional1-32
timestamps_granularitystring or nullOptional
diarizeboolean or nullOptional
diarization_thresholddouble or nullOptional0.1-0.4
additional_formatsstring or nullOptional
file_formatstring or nullOptional
cloud_storage_urlstring or nullOptional
source_urlstring or nullOptional
webhookboolean or nullOptional
webhook_idstring or nullOptional
temperaturedouble or nullOptional0-2
seedinteger or nullOptional0-2147483647
use_multi_channelboolean or nullOptional
webhook_metadatastring or nullOptional
entity_detectionstring or nullOptional
no_verbatimboolean or nullOptional
detect_speaker_rolesboolean or nullOptional
entity_redactionstring or nullOptional
entity_redaction_modestring or nullOptional
keytermslist of strings or nullOptional
with_timestampsboolean or nullOptional
debug_modeboolean or nullOptional

Response

Successful Response
textstring

Errors

422
Unprocessable Entity Error