Report Bug / Feature Request
AI Transcription Live Transcription YouTube Transcription Meeting Transcription Podcast Transcription Zoom Transcription Audio to Text Video to Text More →

Interview Transcription

Commercial use OK 380+ models No watermark No sign-up needed
Model:
+ GPT-5, Claude, Gemini
1-on-1 interview transcription with 2-speaker diarization. Rename the labels (Interviewer / Interviewee, or the actual names) before submit — every quote gets timestamped and the output exports as readable Q&A ready for your journalism writeup, podcast show notes, or research dataset.

Drag and drop your interview recording, or click to browse

MP3, WAV, M4A, MP4 — up to 1GB. Phone recordings (mono, 8 kHz) supported.

— — — —
Speaker diarization is always on for this tool (2 speakers forced). Labels default to your names above — editable post-transcription.
Token estimate for this interview
—
Interview transcript

Transcribing interview and identifying speakers...

Usually 30s-3min depending on length.

Built for journalists, researchers + qualitative interviewers

Journalism + writeups

Export the Q&A TXT with timestamps — quote with confidence, cite the exact second, paste straight into your story or newsroom CMS.

Qualitative research

Export JSON for coding in NVivo/Atlas.ti/Dedoose. Every turn has start/end timestamps + speaker labels — ready for thematic analysis.

HR + hiring interviews

Transcribe candidate calls with consent. DOCX export with speaker labels makes it easy to share with the hiring panel.

How interview transcription works

  1. Drop your recording on the upload zone — MP3/WAV/MP4 up to 1GB. Works with phone interviews.
  2. Rename Speaker 1 and Speaker 2 to the actual names (or leave defaults).
  3. Check the quote and click Transcribe. We do 2-speaker diarization automatically.
  4. Get a clean Q&A transcript. Download TXT/DOCX/SRT/VTT/JSON with your custom speaker names applied.

Free.ai vs Rev.com, Otter, Trint

Feature Free.ai Rev.com (AI) Otter.ai Trint
Price$0.003/min$1.50/min$16.99/mo$60/mo
Rename speaker labels pre-submitPost-editPost-editPost-edit
DOCX exportPaid
Languages9930+English-focused30+
Public APILimited
Sign-up requiredNoYesYesYes
Competitor pricing reflects publicly-listed 2026 tiers.
Advanced options
Result
Tokens running low. Get More Tokens
Want better results? Premium models (GPT-5, Claude, Gemini) deliver higher quality. View Plans

❤️ Love Free.ai? Tell your friends!

Sign up to get a referral link and earn 25,000 tokens per friend.

Want more? Sign up free for 5K tokens/day + 10K bonus
Sign Up Free

Processing your request...

Transcribe interviews with free AI. Automatic speaker labeling and timestamps.

How to Use Interview Transcription

1
Enter your input

Type text, upload a file, or describe what you want. No account needed.

2
Click generate

Our AI processes your request in seconds using the best open-source models.

3
Download & share

Download, copy, or share your result. Free for personal and commercial use.

Use this tool via API

Automate this tool from your own code. OpenAI-compatible REST endpoint, Bearer-token auth, no extra SDK required. Token costs match the web interface.

API Documentation Get API Key 
curl -X POST https://api.free.ai/v1/stt/ \
  -H "Authorization: Bearer sk-free-..." \
  -H "Content-Type: application/json" \
  -d '{"file": "@audio.mp3", "language": "auto"}'

Related Free AI Tools

AI Transcription
Live Transcription
YouTube Transcription
Meeting Transcription
Podcast Transcription
Zoom Transcription
Audio to Text
Video to Text

Interview Transcription — FAQ

Interview mode forces 2-speaker diarization and lets you rename the labels to "Interviewer" and "Interviewee" (or custom names). Every speaker turn gets a clean timestamp, and the output ships as readable Q&A pairs ready for a journalist writeup.

MP3, WAV, M4A, FLAC, OGG, MP4, WebM, MOV and any other format ffmpeg can decode. Phone interviews (mono, 8 kHz) work — Whisper handles the low bit-rate gracefully.

Yes. Set labels before submitting (defaults to "Interviewer" / "Interviewee") or edit them in the result view — every segment updates in place and the export uses your names.

Rev charges $1.50/minute for AI transcription and $1.99+/minute for human-verified. We use the same Whisper-large-v3 model Rev offers in their AI tier, at ~500 tokens/min (roughly $0.003/min — 500x cheaper than Rev AI).

Otter caps at 300 free minutes per month and is English-only. We support 99 languages on Whisper-large-v3, no monthly cap, pay-as-you-go.

Trint starts at $60/month for 7 hours. We charge per-use — roughly $0.003/min. For an occasional journalist doing 10-20 interviews a year, Free.ai is essentially free; for a newsroom doing hundreds, our pricing still beats Trint by 50-80%.

TXT (clean Q&A format with timestamps), SRT (for video-interview subtitles), VTT, JSON (for post-processing), and DOCX (Microsoft Word — ready for editors).

Yes — phone audio (mono, 8 kHz) works fine. Upload your recording (Google Voice, OpenPhone, a .wav from a handheld recorder, etc.). Accuracy is typically 92-96% for clean phone audio.

Very high for clean audio with minimal crosstalk (>95% correct speaker attribution). Accuracy drops when both speakers talk over each other — split those clips into two separate uploads if needed.

Audio files are deleted after transcription. Transcripts are stored under your account for 7 days (paid) or 24 hours (free). For anything sensitive, download the TXT/DOCX and delete the history row.

Yes — the "Timestamps" view shows every turn with its start time. Copy the quote + timestamp straight into your article for verifiability, or use the JSON export for programmatic citation.

Use /transcribe/meeting/ instead — that tool lets you set 2-10 speakers. The /transcribe/interview/ tool is optimized for 1-on-1 format.

Sign up free for 10,000 tokens

Create Free Account

No credit card required

How would you rate this tool?

Love Free.ai? Tell your friends!