VoiceLabsTranscription and captures
Transcribe audio with VoiceLabs' hosted Whisper. Transcripts are stored as captures on your account, listable from the MCP server and the API.
VoiceLabs can turn audio into text using its hosted Whisper speech-to-text, running on VoiceLabs' GPU servers.
Captures
Every transcription creates a capture on your account — a record of the audio (dictations, recordings, uploads) together with its transcript. Your recent captures, with transcripts, can be listed from the surfaces below.
How to transcribe today
Transcription is live on two surfaces:
- MCP — the
transcribetool accepts an audio clip (base64, up to 10 MiB of base64, with an optional language) and returns the transcript plus the created capture id. See Connecting AI assistants. - API —
POST /v1/transcriptionsdoes the same over REST with an API key, andGET /v1/captureslists your captures (paginated). See Developer API.
Metered server-side
Transcription runs on VoiceLabs' GPUs and is metered server-side by your plan. See Usage and limits.
Voices and engines
Voice profiles, the planned seven-engine TTS lineup (Qwen3-TTS, Chatterbox, Kokoro, and more), and the rules around voice cloning.
Usage and limits
How VoiceLabs meters usage — the free monthly generation allowance and the Pro plan's 120 minutes of generated audio per month, fair use.