/audio-processing | Type: Embedded | PCID required: No
Convert text to speech with configurable voices and emotions. Transcribe audio and video files with speaker diarization, summaries, and sentiment analysis.
Tools
| Tool | Description |
|---|---|
audio-processing_text_to_speech | Convert text to speech |
audio-processing_transcribe_audio_or_video | Transcribe audio or video to text |
audio-processing_text_to_speech
Convert text to speech with configurable voice, pitch, speed, volume, and emotion settings. Parameters:| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
text | string | Yes | — | Text to convert to speech (max 5000 characters) |
voice_id | enum | No | "Wise_Woman" | Voice to use: "Wise_Woman", "Friendly_Person", "Inspirational_girl", "Deep_Voice_Man", "Calm_Woman", "Casual_Guy", "Lively_Girl", "Patient_Man", "Young_Knight", "Determined_Man", "Lovely_Girl", "Decent_Boy", "Imposing_Manner", "Elegant_Man", "Abbess", "Sweet_Girl_2", "Exuberant_Girl" |
pitch | number | No | 0 | Voice pitch adjustment (-12 to 12) |
speed | number | No | 1 | Speech speed multiplier (0.5 to 2) |
volume | number | No | 1 | Volume level (0 to 10) |
emotion | enum | No | "auto" | Emotional tone: "auto", "neutral", "happy", "sad", "angry", "fearful", "disgusted", "surprised" |
sample_rate | number | No | 32000 | Audio sample rate in Hz |
language_boost | enum | No | "None" | Language to boost for pronunciation accuracy. Supports many languages including English, Spanish, French, German, Chinese, Japanese, Korean, and more. |
| Field | Type | Description |
|---|---|---|
output | object[] | Array of audio output objects |
output[].url | string | URL of the generated audio file |
output[].mimeType | string | MIME type of the generated audio |
audio-processing_transcribe_audio_or_video
Transcribe audio or video files to text. Supports speaker diarization, paragraph formatting, summaries, topic detection, sentiment analysis, and content redaction. Parameters:| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
fileUrl | string | Yes | — | URL of the audio or video file to transcribe |
model | enum | No | "nova-3" | Transcription model: "nova-3", "nova-2", "enhanced", "base" |
languageCode | string | No | — | Language code (auto-detected if not specified) |
enableDiarization | boolean | No | false | Enable speaker diarization to identify different speakers |
diarizationSpeakerCount | number | No | — | Expected number of speakers (1–10, improves diarization accuracy) |
enableParagraphs | boolean | No | false | Format transcription into paragraphs |
enableSummary | boolean | No | false | Generate a summary of the transcription |
enableTopics | boolean | No | false | Detect topics discussed in the audio |
enableSentiment | boolean | No | false | Analyze sentiment of the transcription |
redact | enum[] | No | — | Content types to redact: "pci", "pii", "phi", "numbers", "ssn", and others |
| Field | Type | Description |
|---|---|---|
transcription | string | The transcribed text |
metadata | object | Transcription metadata (duration, model, language, etc.) |
summary | string | Summary of the transcription (when enableSummary is true) |
topics | object | Detected topics (when enableTopics is true) |
sentiment | object | Sentiment analysis results (when enableSentiment is true) |
utterances | object[] | Speaker-attributed segments (when enableDiarization is true) |
utterances[].speaker | string | Speaker identifier |
utterances[].start | number | Start time in seconds |
utterances[].end | number | End time in seconds |
utterances[].text | string | Text spoken by the speaker |