What is Nova-2 Phonecall API?
Nova-2: Advanced, versatile ASR model for diverse transcription needs.
Technical Specifications
- Supported inputs: Audio
- Output: Text
Performance Benchmarks
[embed]
Nova-2 Phonecall API Pricing
- Pricing on request
Where to Use Nova-2 Phonecall
Transcription
Convert calls, meetings, and media into accurate, searchable text.
Captioning and indexing
Generate subtitles and make audio archives searchable.
Live phone-line transcription is a documented fit for Nova-2 Phonecall, which is optimized for low-bandwidth audio phone calls and is described as appropriate when the agent runs on a live phone line.
Real-time contact center transcription and automation are listed as use cases for the model, including Amazon Connect and Lex workflows built around phone-call audio.
Streaming transcription for live captioning is also documented, with the model described as supporting real-time streaming over WebSocket and being suited to live captioning and streaming transcription.
Multi-speaker conversation transcription is another documented use case, with the model positioned for multi-speaker conversations on phone-call audio.
import requests, time headers = {"Authorization": "Bearer " + AIMLAPI_KEY} job = requests.post( "https://api.aimlapi.com/v1/stt/create", headers=headers, json={ "model": "deepgram/nova-2-phonecall", "url": "https://example.com/audio.mp3" }, ).json() gid = job["generation_id"] while True: res = requests.get(f"https://api.aimlapi.com/v1/stt/{gid}", headers=headers).json() if res.get("status") in ("completed", "error", "failed"): break time.sleep(3) print(res)
const headers = { Authorization: `Bearer ${process.env.AIMLAPI_KEY}`, "Content-Type": "application/json", }; const job = await (await fetch("https://api.aimlapi.com/v1/stt/create", { method: "POST", headers, body: JSON.stringify({ "model": "deepgram/nova-2-phonecall", "url": "https://example.com/audio.mp3" }), })).json(); let res; do { await new Promise((r) => setTimeout(r, 3000)); res = await (await fetch(`https://api.aimlapi.com/v1/stt/${job.generation_id}`, { headers })).json(); } while (!["completed", "error", "failed"].includes(res.status)); console.log(res);
# submit the job — the response contains "generation_id" curl -X POST https://api.aimlapi.com/v1/stt/create \ -H "Authorization: Bearer $AIMLAPI_KEY" \ -H "Content-Type: application/json" \ -d '{"model":"deepgram/nova-2-phonecall","url":"https://example.com/audio.mp3"}' # then poll for the result until it is ready curl "https://api.aimlapi.com/v1/stt/{generation_id}" -H "Authorization: Bearer $AIMLAPI_KEY"
OpenAI-compatible — swap the base URL and it works with your existing SDK.
| Type | Price |
|---|---|
| Output | |
| Model | Input | Output | Context | Best for |
|---|---|---|---|---|
Nova-2 Phonecall This page | Transcription | |||
| Speech synthesis | ||||
| Speech synthesis | ||||
| Speech synthesis | ||||
| Speech synthesis |
Nova-2 Phonecall takes audio as input and returns text.
Nova-2 Phonecall became available on December 30, 2025.
Nova-2 Phonecall is priced at output $0.00009317 / sec.
Nova-2 Phonecall was built by Deepgram.
Use deepgram/nova-2-phonecall as the model id on AI/ML API.
Yes. Nova-2 Phonecall is served through AI/ML API, so the same key and endpoint format used for other models applies.
The model ID is deepgram/nova-2-phonecall.