Audio Transcription
AutoTalk turns audio into text in two ways:
- Automatic chat transcription — inbound voice notes on your channels are transcribed inline so agents and AI assistants can read them immediately.
- Standalone transcription — transcribe any audio file in your storage
(interviews, meetings, podcasts — hours long if needed) into downloadable
.txt,.srt,.vttand.jsontranscripts, optionally with speaker labels.
Both are configured through transcription profiles.
Transcription profiles
A profile is a reusable, company-wide transcription configuration. Manage them under Company → Transcription profiles. Every company starts with a default OpenAI (platform) profile, so transcription works out of the box.
| Provider type | What it does | Billing |
|---|---|---|
openai | Uses OpenAI Whisper. With no API key set it uses AutoTalk's platform key; set your own OpenAI key to make it BYOK. | With the platform key (no API key), billed as audio minutes on your AutoTalk invoice. With your own OpenAI key it's BYOK — billed by your provider, not as AutoTalk audio minutes. |
openai_compatible | Sends audio to your own Whisper-compatible endpoint (your OpenAI key, Groq, a self-hosted faster-whisper server, …). | Billed by your provider; AutoTalk only tracks usage. |
diarize | Sends audio to a self-hosted WhisperX box that also identifies who spoke (speaker diarization). | Billed by you (your hardware); AutoTalk only tracks usage. |
Profile fields:
- Name — shown in pickers.
- Provider type — one of the three above.
- Base URL — your endpoint (BYO providers only). Must be a public HTTP(S) URL.
- Model — optional model override (defaults to
whisper-1). - Language — default transcription language (empty uses your company locale).
- API key — your provider key or self-hosted shared secret, stored encrypted and sent as a Bearer token.
- Headers — optional extra HTTP headers sent to BYO provider endpoints
(shown for
openai_compatible/diarizeprofiles). - Company default — the profile used whenever a channel or job doesn't pick one explicitly.
Channels can pin a specific profile in the channel's Transcription
options. Channels only accept openai / openai_compatible profiles —
diarization is for standalone jobs (voice notes have a single speaker).
Transcribing a file from Storage
- Open Company → Storage, select an audio file, and pick Transcribe (context menu or the details panel).
- Choose the profile, language and output formats. If the profile is a diarization profile, the transcript will label speakers.
- Click Transcribe. The dialog switches to a live progress view — you can close it at any time; the job keeps running in the background.
- Track jobs in the Transcriptions panel (side menu or the shortcut in the Storage toolbar). When a job finishes you'll also get a notification.
- Outputs are saved next to the source file as
<name>.transcript.<jobId>.txt/srt/vtt/json(the job id keeps each run's output distinct so re-runs never collide), and the panel offers downloads, a copy button and a read-only viewer with timestamps and speaker labels.
Long files are handled automatically: the audio is split into chunks, transcribed in parallel and stitched back with correct timestamps (up to 4 hours per file; diarized jobs up to 90 minutes).
Self-hosted diarization (WhisperX)
Speaker labels come from a self-hosted WhisperX + pyannote service you
run on your own GPU machine (12 GB VRAM recommended; smaller cards work with
the int8 option). Setup — including the required Hugging Face token for the
gated pyannote models — is documented in the
autotalk-transcription-gpu
repository README. Point a diarize profile at your box's URL with the
shared secret as the API key, and it becomes available in the Transcribe
dialog.
API
Transcription jobs are also available programmatically:
POST /v1/transcriptions— enqueue a job (fullPath, optionalprofileId,languageCode,formats).GET /v1/transcriptions/{id}— job status, progress and output paths.
MCP-connected assistants can call the transcribe_storage_file and
get_transcription_job tools for the same flow.
Billing details
- Platform (
openai) transcription bills the audio minutes meter, normalized by provider cost, and respects your plan's monthly limits. - BYO and self-hosted profiles are not billed by AutoTalk — usage is tracked internally for your reference only.
- Audio preparation (normalization/splitting) bills the transcoding meter, like other media processing.