API Limits

Character limits

Rate limits

Rate limits differ by product because the workloads differ. Build audio is cost-per-call. Agents is chatty interactive traffic.

Build audio

Applies to /v1/audio/speech and /v1/audio/stream.

Agents

Applies to every Agents endpoint under /v1/agents/*: agents, conversations, knowledge bases, tools, tests, memories, audio assets, batch calls, IVR menus, and telephony.

Concurrency limits

Concurrency limits cap the number of simultaneous in-flight requests per account.

Build audio

Applies to /v1/audio/speech and /v1/audio/stream.

Agents

Applies to the authenticated Agents endpoints listed above. The primary target is POST /v1/agents/{id}/conversations, which allocates a live-call session.

Reading your budget

Every response on a rate-limited endpoint carries the request-rate budget headers, so clients can pace themselves before hitting 429:

The same values are mirrored as X-RateLimit-* for clients predating the IETF draft names.

Every Speechify-specific header follows the same rule: the canonical name is un-prefixed and namespaced (Speechify-Request-Id, Speechify-Version, Speechify-Signature), and any pre-2026 X- spelling is still accepted and still emitted alongside it until 2027-07-24.

Handling 429 responses

When you exceed rate or concurrency limits, the API returns 429 Too Many Requests with a Retry-After header. The error body names the limit your plan allows and links back to this page (error.docs_url); the two cases are distinguishable by error.code: rate_limited (requests per second) vs concurrency_limited (simultaneous requests).

Need more headroom? Every limit above rises with your plan - upgrade in the console under Billing, or contact us for Enterprise terms.

1
import time
2
from speechify import Speechify
3
4
client = Speechify()
5
6
def generate_with_retry(text, max_retries=3):
7
    for attempt in range(max_retries):
8
        try:
9
            return client.audio.speech(
10
                input=text,
11
                voice_id="geffen_32",
12
                model="simba-3.2",
13
                audio_format="mp3",
14
            )
15
        except Exception as e:
16
            if "429" in str(e) and attempt < max_retries - 1:
17
                time.sleep(2 ** attempt)
18
            else:
19
                raise

Processing long texts

For texts exceeding 20,000 characters, split into chunks and process sequentially:

1
def split_text(text, max_chars=19000):
2
    """Split text at sentence boundaries within the character limit."""
3
    chunks = []
4
    current = ""
5
    for sentence in text.split(". "):
6
        if len(current) + len(sentence) + 2 > max_chars:
7
            chunks.append(current.strip())
8
            current = sentence + ". "
9
        else:
10
            current += sentence + ". "
11
    if current.strip():
12
        chunks.append(current.strip())
13
    return chunks

FAQ