Speechmatics is an automatic speech recognition (ASR) platform that provides high-quality transcription and translation services for a variety of industries, including media, entertainment, and call center operations. The app utilizes advanced machine learning algorithms to accurately transcribe speech in real-time, supporting over 30 languages and dialects.

Speechmatics also offers a custom dictionary feature, allowing users to add their own industry-specific vocabulary, and has a built-in time-stamping function for easy editing. The platform can be accessed through a web interface or integrated into other software applications via API.

Supported Operations

Speechmatics ASR REST API

List All Jobs

Retrieve a list of all jobs initiated for Automatic Speech Recognition (ASR). This endpoint provides paginated results and allows you to filter jobs by creation time, set result limits, and include deleted jobs. By default, it starts with the most recent jobs.

Create a New Job

This endpoint allows you to submit a new job for Automatic Speech Recognition (ASR). It initiates the processing of audio data to transcribe spoken content into text. Use this operation to create a new ASR job.

Get job Details, Including Progress and any Error Reports

Retrieve detailed information about a specific job, including its progress and any error reports, using the job's unique ID.

Delete a Job and Remove All Associated Resources

Delete a specific job and remove all associated resources, including audio data and transcripts, using the job's unique ID. Optionally, you can force terminate a running job by setting the force parameter. If force is unset (default), a running job will not be terminated and the request will return HTTP 423 Locked.

Get the Aligned text File for an Alignment Job

Retrieve the aligned text file for a specific alignment job identified by its unique job ID. You can control how timing information is added to the text file using the tags parameter. Set it to word_start_and_end to insert SGML tags at the start and end of each word, or one_per_line to insert square bracket tags at the start of each line. The default is word_start_and_end.

Get the Transcript for a Transcription Job

Retrieve the transcript for a specific transcription job identified by its unique job ID. You can specify the transcription format using the format parameter; by default, the json-v2 format is returned. Use this endpoint to access the text transcript of the audio content.

Get the Usage Statistics

Retrieve usage statistics, including data since and until specific dates. Use the since and until parameters to specify the date range in ISO-8601 calendar date format (e.g., `YYYY-MM-DD`). This endpoint provides insights into your usage of the service.

Last Update

1 week ago