InfiniteTalk Serverless API
Full-body animation from images synchronized perfectly to audio.
POST /v2/infinite-talk · submit + poll 1# pip install "segmind>=1.1.0"
2# export SEGMIND_API_KEY="YOUR_API_KEY"
3from segmind import SegmindClient, InferenceFailed, InferenceTimeout
4
5# Async (v2) — recommended for long-running / video models.
6# run() blocks up to 600s; submit_async + job.wait(timeout=...) sets a longer
7# deadline and keeps the request_id so you can re-poll later.
8client = SegmindClient() # reads SEGMIND_API_KEY
9payload = {
10 "prompt": "A professional woman speaks confidently, gesturing naturally while addressing the camera.",
11 "image": "https://segmind-resources.s3.amazonaws.com/input/infinite-talk-example-ip.png",
12 "audio": "https://segmind-resources.s3.amazonaws.com/input/infinite-talk-example-audio.mp3",
13 "seed": 42424242,
14 "resolution": "480p",
15 "fps": 25,
16 "base64": False,
17}
18job = client.submit_async("infinite-talk", **payload)
19print(job.request_id) # available immediately
20try:
21 result = job.wait(timeout=900, interval=2.0)
22 print(result["status"]) # COMPLETED
23 print(result.get("output")) # model output (e.g. video URL)
24except InferenceTimeout as e:
25 print("still running:", e.request_id) # re-poll later with this id
26except InferenceFailed as e:
27 print("failed:", e.detail)
28
29# Fast models (<=600s) can use the one-liner instead:
30# result = segmind.run("infinite-talk", **payload) 1# pip install "segmind>=1.1.0"
2# export SEGMIND_API_KEY="YOUR_API_KEY"
3from segmind import SegmindClient, InferenceFailed, InferenceTimeout
4
5# Async (v2) — recommended for long-running / video models.
6# run() blocks up to 600s; submit_async + job.wait(timeout=...) sets a longer
7# deadline and keeps the request_id so you can re-poll later.
8client = SegmindClient() # reads SEGMIND_API_KEY
9payload = {
10 "prompt": "A professional woman speaks confidently, gesturing naturally while addressing the camera.",
11 "image": "https://segmind-resources.s3.amazonaws.com/input/infinite-talk-example-ip.png",
12 "audio": "https://segmind-resources.s3.amazonaws.com/input/infinite-talk-example-audio.mp3",
13 "seed": 42424242,
14 "resolution": "480p",
15 "fps": 25,
16 "base64": False,
17}
18job = client.submit_async("infinite-talk", **payload)
19print(job.request_id) # available immediately
20try:
21 result = job.wait(timeout=900, interval=2.0)
22 print(result["status"]) # COMPLETED
23 print(result.get("output")) # model output (e.g. video URL)
24except InferenceTimeout as e:
25 print("still running:", e.request_id) # re-poll later with this id
26except InferenceFailed as e:
27 print("failed:", e.detail)
28
29# Fast models (<=600s) can use the one-liner instead:
30# result = segmind.run("infinite-talk", **payload)API Endpoint
https://api.segmind.com/v1/infinite-talkParameters
audiorequiredstring (uri)URL of the audio file to synchronize with the animation. Use clear speech recordings; start with 5–15 second clips for faster iteration and testing.
imagerequiredstring (uri)URL of the source image or video to animate with audio-driven full-body motion. Use high-resolution, well-lit images for better identity and background preservation.
promptrequiredstringDescribe the scene, emotion, or action guiding the full-body animation. Try specific phrases like 'A speaker gestures confidently while presenting to an audience.'
"A professional woman speaks confidently, gesturing naturally while addressing the camera."base64optionalbooleanEncodes the output video as a Base64 string instead of a file URL. Keep false for standard URL-based delivery; set true only if your integration requires raw encoded output.
falsefpsoptionalintegerFrames per second for the output video. Use 16–20 for fast test renders; set 25–30 for smooth, production-quality animations.
25Range: 16 - 30resolutionoptionalstringSets the output video resolution. Use 480p for quick drafts and iteration; choose 720p for final high-quality renders and presentations.
"480p""480p""576p""720p"seedoptionalintegerControls output randomness for reproducible results. Fix the seed for consistent animations; vary it to explore different motion styles from the same inputs.
42424242Response Type
Returns: Video
Asynchronous requests (v2)
Use Async for video, long-running (>~60s), or high-concurrency workloads; Sync is simplest for fast image & LLM calls. Async submits a request and you poll it to completion.
- 1
POST /v2/infinite-talkSubmit — returns request_id, status_url, response_url
- 2
GET /v2/requests/{id}/statusPoll — until COMPLETED or FAILED
- 3
GET /v2/requests/{id}Result — final response body
Status states
- A FAILED request is served as HTTP 422 — the body still carries the error detail.
- An unknown or expired request_id returns HTTP 404.
- Results are retained for 1 hour, then expire.
- Content / RAI blocks surface as FAILED, not a separate state.
- Track completion by polling the status endpoint.
Common Error Codes
The API returns standard HTTP status codes. Detailed error messages are provided in the response body.
Bad Request
Invalid parameters or request format
Unauthorized
Missing or invalid API key
Forbidden
Insufficient permissions
Not Found
Model or endpoint not found
Insufficient Credits
Not enough credits to process request
Rate Limited
Too many requests
Server Error
Internal server error
Bad Gateway
Service temporarily unavailable
Timeout
Request timed out