API Limits

Character limits

Rate limits

Rate limits are tuned per product because the workloads differ: TTS audio is cost-per-call, voice agents is chatty interactive UI traffic.

TTS audio

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

Voice agents

Applies to /v1/agents/*, /v1/tools/*, /v1/conversations/*, /v1/tests/*, /v1/knowledge-bases/*, and /v1/memories/*.

Concurrency limits

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

TTS audio

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

Voice agents

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

Handling 429 responses

When you exceed rate or concurrency limits, the API returns 429 Too Many Requests with a Retry-After header.

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.tts.audio.speech(
10
                input=text,
11
                voice_id="george",
12
                audio_format="mp3",
13
            )
14
        except Exception as e:
15
            if "429" in str(e) and attempt < max_retries - 1:
16
                time.sleep(2 ** attempt)
17
            else:
18
                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