# Azure AI Speech integration

> Microsoft Azure Speech service for speech-to-text transcription, text-to-speech synthesis, pronunciation assessment, and speaker recognition

- Authentication: apiKey

## Tools (97)

- **Authorize Custom Model Copy**: Authorize another Speech resource to copy custom models into this one.
- **Commit Dataset Blocks**: Finalize a block-based dataset upload by committing the ordered list of previously uploaded block IDs.
- **Copy Custom Speech Model**: Copy a custom model from another Speech resource into this one using an authorization payload.
- **Create Batch Synthesis**: Create an asynchronous long-form text-to-speech synthesis job for audio longer than 10 minutes.
- **Create Custom Speech Endpoint**: Deploy a custom speech-to-text model to a hosted endpoint for real-time recognition.
- **Create Custom Speech Model**: Train a new custom speech-to-text model from a base model and training datasets.
- **Create Custom Speech Project**: Create a project to group custom speech models, datasets, and endpoints for a single locale.
- **Create Custom Voice Endpoint**: Deploy a trained custom voice model to a hosted endpoint for TTS synthesis.
- **Create Custom Voice Model**: Train a professional custom voice model from a training set and consent.
- **Create Custom Voice Project**: Create a professional or personal custom voice project.
- **Create Dataset**: Upload and register a dataset (audio, transcripts, pronunciation) for training or testing a custom speech model.
- **Create Evaluation**: Create an accuracy evaluation comparing two custom speech-to-text models against a test dataset.
- **Create Identification Profile**: Create a text-independent speaker identification profile.
- **Create Personal Voice from File Upload**: Create a personal voice by uploading one or more audio files as multipart form data.
- **Create Personal Voice from URL**: Create a personal voice by fetching audio samples from an Azure Blob container.
- **Create Text-Independent Verification Profile**: Create a text-independent speaker verification profile that accepts any spoken content.
- **Create Verification Profile**: Create a text-dependent speaker verification profile for a single speaker.
- **Create Voice Consent**: Register a voice-talent or user consent audio recording required to train a custom voice.
- **Create Voice Training Set**: Create a training set of paired audio and transcripts for professional voice fine-tuning.
- **Create Webhook**: Register a webhook to receive notifications about custom speech and batch transcription lifecycle events.
- **Delete Batch Synthesis**: Delete a batch text-to-speech synthesis job and its output files.
- **Delete Custom Speech Endpoint**: Delete a deployed custom speech-to-text endpoint.
- **Delete Custom Speech Model**: Delete a custom speech model.
- **Delete Custom Speech Project**: Delete a custom speech project. Does not delete referenced datasets, models, or endpoints.
- **Delete Custom Voice Endpoint**: Delete a deployed custom voice endpoint.
- **Delete Custom Voice Model**: Delete a professional custom voice model.
- **Delete Custom Voice Project**: Delete a custom voice project.
- **Delete Dataset**: Delete a custom-speech dataset.
- **Delete Evaluation**: Delete an evaluation and its result files.
- **Delete Identification Profile**: Delete a text-independent speaker identification profile and its enrollment audio.
- **Delete Personal Voice**: Delete a personal voice and its speaker profile.
- **Delete Transcription**: Delete a batch transcription job and its associated result files.
- **Delete Verification Profile**: Delete a text-dependent speaker verification profile and its enrollment audio.
- **Delete Voice Consent**: Delete a voice consent record.
- **Delete Voice Training Set**: Delete a professional voice training set.
- **Delete Webhook**: Delete a registered webhook.
- **Enroll Identification Profile**: Add enrollment audio to a text-independent speaker identification profile.
- **Enroll Text-Independent Verification Profile**: Add enrollment audio to a text-independent verification profile.
- **Enroll Verification Profile**: Add an enrollment audio sample to a text-dependent verification profile.
- **Fast Transcribe Audio**: Synchronously transcribe an audio file up to 2 hours and 200 MB with predictable low latency and speaker diarization.
- **Get Batch Synthesis**: Get the status and output URL of a batch synthesis job.
- **Get Custom Speech Endpoint**: Get details of a deployed custom speech-to-text endpoint by ID.
- **Get Custom Speech Model**: Get a single custom speech-to-text model by ID including training status.
- **Get Custom Speech Project**: Get a single custom speech project by ID.
- **Get Custom Voice Long-Running Operation**: Poll the status of a custom voice async operation (personal voice create, model train, endpoint suspend/resume).
- **Get Dataset**: Get a single custom-speech dataset by ID.
- **Get Evaluation**: Get details and results of a single custom speech evaluation.
- **Get Identification Profile**: Get a single text-independent speaker identification profile by ID.
- **Get Personal Voice**: Get a personal voice by ID including its speakerProfileId for SDK synthesis.
- **Get Transcription**: Get the status and metadata of a batch transcription job by ID.
- **Get Transcription File**: Get metadata for one specific output file of a transcription, including a signed content URL.
- **Get Verification Profile**: Get a single text-dependent speaker verification profile by ID.
- **Get Webhook**: Get a single webhook by ID.
- **Identify Speaker**: Identify which of a set of enrolled speakers is speaking in an audio sample.
- **List Base Speech-to-Text Models**: List available base speech-to-text models (including Whisper) for use with batch and custom transcription.
- **List Batch Syntheses**: List all batch text-to-speech synthesis jobs for the Speech resource.
- **List Custom Model Files**: List output artifacts (logs, reports) produced by training a custom model.
- **List Custom Speech Endpoints**: List all deployed custom speech-to-text endpoints in the resource.
- **List Custom Speech Models**: List custom speech-to-text models in the resource.
- **List Custom Speech Projects**: List all custom speech projects in the Speech resource.
- **List Custom Voice Endpoints**: List deployed custom voice endpoints.
- **List Custom Voice Models**: List professional custom voice models.
- **List Custom Voice Projects**: List all custom voice projects in the Speech resource.
- **List Dataset Files**: List individual files that make up a dataset.
- **List Datasets**: List custom-speech datasets in the resource.
- **List Evaluation Files**: List result files (per-utterance transcripts, summary report) of an evaluation.
- **List Evaluations**: List custom speech accuracy evaluations in the resource.
- **List Identification Activation Phrases**: List optional activation phrases for text-independent speaker identification enrollment.
- **List Identification Profiles**: List all text-independent speaker identification profiles.
- **List Personal Voices**: List personal voices in the Speech resource.
- **List Speaker Verification Phrases**: List valid pass phrases that a speaker must speak during text-dependent verification enrollment.
- **List Supported Transcription Locales**: List BCP-47 locale codes supported by offline (batch) transcription.
- **List Transcription Files**: List the output files (transcripts, report) of a completed batch transcription.
- **List Transcriptions**: List all batch transcription jobs for the Speech resource.
- **List Verification Profiles**: List all text-dependent speaker verification profiles.
- **List Voice Consents**: List voice-talent and user consent records for custom voice projects.
- **List Voices**: Get the full list of neural text-to-speech voices available for a region, with locale, gender, styles, and sample rates.
- **List Voice Training Sets**: List training sets across professional voice projects.
- **List Webhooks**: List all registered webhooks for the Speech resource.
- **Ping Webhook**: Send a synthetic ping event to a registered webhook URL to verify reachability.
- **Recognize Short Audio**: Transcribe up to 60 seconds of audio synchronously and return recognized text with confidence scores.
- **Reset Identification Profile**: Clear enrollments on a text-independent speaker identification profile.
- **Reset Verification Profile**: Clear all enrollments on a text-dependent verification profile without deleting the profile.
- **Resume Custom Voice Endpoint**: Resume a suspended custom voice endpoint.
- **Submit Batch Transcription**: Create an asynchronous transcription job for one or more audio files in Azure Blob storage.
- **Suspend Custom Voice Endpoint**: Suspend a custom voice endpoint to stop billing without deleting deployment metadata.
- **Synthesize Speech (Text to Speech)**: Convert SSML or text to synthesized audio in real time, returning the audio bytes directly in the response body.
- **Test Webhook**: Send one synthetic event of each subscribed event type to a registered webhook URL.
- **Update Custom Speech Endpoint**: Update mutable metadata on a custom speech-to-text endpoint.
- **Update Custom Speech Model**: Update mutable metadata on a custom model.
- **Update Custom Speech Project**: Update mutable fields of a custom speech project.
- **Update Dataset**: Update mutable fields of a dataset (displayName, description, project, customProperties).
- **Update Transcription**: Update mutable fields (displayName, description, project) on an existing transcription job.
- **Update Webhook**: Update a webhook's URL, events subscription, or metadata.
- **Upload Dataset Block**: Upload one 8 MiB block of a dataset for block-based content upload.
- **Verify Speaker**: Verify whether an audio sample matches an enrolled text-dependent verification profile.
- **Verify Text-Independent Speaker**: Verify whether an audio sample matches an enrolled text-independent verification profile.

## Related prompts

- [Log Dropbox support calls to Zendesk with Azure Speech](https://www.generalinput.com/prompts/log-dropbox-support-calls-to-zendesk-with-azure-speech.md)
- [Turn Google Drive meeting recordings into Notion notes](https://www.generalinput.com/prompts/turn-google-drive-meeting-recordings-into-notion-notes.md)
- [Hourly HubSpot notes from Drive sales calls with Azure Speech](https://www.generalinput.com/prompts/hourly-hubspot-notes-from-drive-sales-calls-with-azure-speech.md)
- [Turn new WordPress posts into narrated MP3s in Google Drive](https://www.generalinput.com/prompts/turn-new-wordpress-posts-into-narrated-mp3s-in-google-drive.md)

Connect Azure AI Speech in General Input: https://www.generalinput.com/apps/azure-ai-speech