speech_to_text
Transcribe audio and video files or URLs into text with speaker diarization, entity detection, and word-level timestamps. Supports multiple languages and webhooks.
Instructions
Speech To Text Spends ElevenLabs credits.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| seed | No | If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result. Determinism is not guaranteed. Must be an integer between 0 and 2147483647. | |
| token | No | A single-use authentication token created via POST /v1/single-use-token/batch_scribe. This token can only be used once and expires after 15 minutes. Alternative to API key or bearer token authentication for frontend clients. | |
| diarize | No | Whether to annotate which speaker is currently talking in the uploaded file. | |
| webhook | No | Whether to send the transcription result to configured speech-to-text webhooks. If set the request will return early without the transcription, which will be delivered later via webhook. | |
| keyterms | No | A list of keyterms to bias the transcription towards. The keyterms are words or phrases you want the model to recognise more accurately. The number of keyterms cannot exceed 1000. The length of each keyterm must be less than 50 characters. Keyterms can contain at most 5 words (after normalisation). | |
| model_id | Yes | The ID of the model to use for transcription. | |
| file_path | No | The file to transcribe (100ms minimum audio length). All major audio and video formats are supported. Exactly one of the file or cloud_storage_url parameters must be provided. The file size must be less than 5.0GB. Local path. | |
| source_url | No | The URL of an audio or video file to transcribe. Supports hosted video or audio files, YouTube video URLs, TikTok video URLs, and other video hosting services. | |
| webhook_id | No | Optional specific webhook ID to send the transcription result to. Only valid when webhook is set to true. If not provided, transcription will be sent to all configured speech-to-text webhooks. | |
| file_base64 | No | Base64 contents for "file". Use this when the server cannot read your local disk. | |
| file_format | No | The format of input audio. Options are 'pcm_s16le_16' or 'other' For `pcm_s16le_16`, the input audio must be 16-bit PCM at a 16kHz sample rate, single channel (mono), and little-endian byte order. Latency will be lower than with passing an encoded waveform. | |
| no_verbatim | No | If true, the transcription will not have any filler words, false starts and non-speech sounds. Only supported with scribe_v2 model. | |
| temperature | No | Controls the randomness of the transcription output. Accepts values between 0.0 and 2.0, where higher values result in more diverse and less deterministic results. If omitted, we will use a temperature based on the model you selected which is usually 0. | |
| num_speakers | No | The maximum amount of speakers talking in the uploaded file. Can help with predicting who speaks when. The maximum amount of speakers that can be predicted is 32. Defaults to null, in this case the amount of speakers is set to the maximum value the model supports. | |
| file_filename | No | Filename to send for "file". Some endpoints infer the audio format from it. | |
| language_code | No | An ISO-639-1 or ISO-639-3 language_code corresponding to the language of the audio file. Can sometimes improve transcription performance if known beforehand. Defaults to null, in this case the language is predicted automatically. | |
| enable_logging | No | When enable_logging is set to false zero retention mode will be used for the request. This will mean log and transcript storage features are unavailable for this request. Zero retention mode may only be used by enterprise customers. | |
| entity_detection | No | Detect entities in the transcript. Can be 'all' to detect all entities, a single entity type or category string, or a list of entity types/categories. Categories include 'pii', 'phi', 'pci', 'other', 'offensive_language'. When enabled, detected entities will be returned in the 'entities' field with | |
| entity_redaction | No | Redact entities from the transcript text. Accepts the same format as entity_detection: 'all', a category ('pii', 'phi'), or specific entity types. Must be a subset of entity_detection. When redaction is enabled, the entities field will not be returned. Usage of this parameter will incur an additiona | |
| tag_audio_events | No | Whether to tag audio events like (laughter), (footsteps), etc. in the transcription. | |
| webhook_metadata | No | Optional metadata to be included in the webhook response. This should be a JSON string representing an object with a maximum depth of 2 levels and maximum size of 16KB. Useful for tracking internal IDs, job references, or other contextual information. | |
| cloud_storage_url | No | [Deprecated] This parameter is deprecated and will be removed in the future. Use 'source_url' instead.The HTTPS URL of the file to transcribe. Exactly one of the file or cloud_storage_url parameters must be provided. The file must be accessible via HTTPS and the file size must be less than 2GB. Any | |
| use_multi_channel | No | Whether the audio file contains multiple channels where each channel contains a single speaker. When enabled, each channel is transcribed independently. By default a separate transcript is returned per channel; set multichannel_output_style='combined' to instead receive a single transcript with all | |
| additional_formats | No | ||
| use_speaker_library | No | Whether to use the speaker library for identifying known speakers during diarization. When enabled and diarize is true, detected speakers will be matched against registered speakers in the workspace's speaker library. | |
| detect_speaker_roles | No | Whether to detect speaker roles (agent vs customer). Requires diarize=true. Cannot be used with use_multi_channel=true. When enabled, speaker_id values will be 'agent' and 'customer' instead of 'speaker_0', 'speaker_1', etc. Usage incurs an additional 10% surcharge on base transcription cost. | |
| diarization_threshold | No | Diarization threshold to apply during speaker diarization. A higher value means there will be a lower chance of one speaker being diarized as two different speakers but also a higher chance of two different speakers being diarized as one speaker (less total speakers predicted). A low value means the | |
| entity_redaction_mode | No | How to format redacted entities. 'redacted' replaces with {REDACTED}, 'entity_type' replaces with {ENTITY_TYPE}, 'enumerated_entity_type' replaces with {ENTITY_TYPE_N} where N enumerates each occurrence. Only used when entity_redaction is set. | |
| timestamps_granularity | No | The granularity of the timestamps in the transcription. 'word' provides word-level timestamps and 'character' provides character-level timestamps per word. | |
| multichannel_output_style | No | Controls the response shape when use_multi_channel is enabled. 'separate' (default) returns one transcript per channel under 'transcripts'. 'combined' merges all channels into a single transcript whose words are sorted by start time, each carrying a 'channel_index' - matching the single-channel resp |