Chatterbox Turbo TTS Serverless API
Ultra-fast, human-quality TTS with emotional expression.
POST /v2/chatterbox-turbo-tts · submit + poll 1# pip install "segmind>=1.1.0"
2# export SEGMIND_API_KEY="YOUR_API_KEY"
3import segmind
4
5# Async (v2): submit to the queue and block until COMPLETED.
6# run() returns the final result dict (600s deadline, 1.0s poll by default).
7result = segmind.run(
8 "chatterbox-turbo-tts",
9 text="Introducing the AI-enhanced Skyline T-800. [laugh] It's got integrated AI for superior performance. Want to explore pricing?",
10 reference_audio="https://segmind-resources.s3.amazonaws.com/output/70e9a9dd-e0f4-450f-a590-872996b44a01-chatterbox-turbo-input.mp3",
11 temperature=0.7,
12 seed=42,
13 min_p=0,
14 top_p=0.9,
15 top_k=500,
16 repetition_penalty=1.3,
17 norm_loudness=True,
18)
19print(result["status"]) # COMPLETED
20print(result.get("output")) # model output (e.g. media URL)
21print(result["metrics"]["inference_time"]) # server compute seconds
22
23# --- Or submit + poll manually (track request_id, control the cadence) ---
24from segmind import SegmindClient, InferenceFailed, InferenceTimeout
25
26client = SegmindClient() # reads SEGMIND_API_KEY
27payload = {
28 "text": "Introducing the AI-enhanced Skyline T-800. [laugh] It's got integrated AI for superior performance. Want to explore pricing?",
29 "reference_audio": "https://segmind-resources.s3.amazonaws.com/output/70e9a9dd-e0f4-450f-a590-872996b44a01-chatterbox-turbo-input.mp3",
30 "temperature": 0.7,
31 "seed": 42,
32 "min_p": 0,
33 "top_p": 0.9,
34 "top_k": 500,
35 "repetition_penalty": 1.3,
36 "norm_loudness": True,
37}
38job = client.submit_async("chatterbox-turbo-tts", **payload)
39print(job.request_id) # available immediately
40try:
41 result = job.wait(timeout=600, interval=1.0)
42except InferenceTimeout as e:
43 print("still running:", e.request_id)
44except InferenceFailed as e:
45 print("failed:", e.detail) 1# pip install "segmind>=1.1.0"
2# export SEGMIND_API_KEY="YOUR_API_KEY"
3import segmind
4
5# Async (v2): submit to the queue and block until COMPLETED.
6# run() returns the final result dict (600s deadline, 1.0s poll by default).
7result = segmind.run(
8 "chatterbox-turbo-tts",
9 text="Introducing the AI-enhanced Skyline T-800. [laugh] It's got integrated AI for superior performance. Want to explore pricing?",
10 reference_audio="https://segmind-resources.s3.amazonaws.com/output/70e9a9dd-e0f4-450f-a590-872996b44a01-chatterbox-turbo-input.mp3",
11 temperature=0.7,
12 seed=42,
13 min_p=0,
14 top_p=0.9,
15 top_k=500,
16 repetition_penalty=1.3,
17 norm_loudness=True,
18)
19print(result["status"]) # COMPLETED
20print(result.get("output")) # model output (e.g. media URL)
21print(result["metrics"]["inference_time"]) # server compute seconds
22
23# --- Or submit + poll manually (track request_id, control the cadence) ---
24from segmind import SegmindClient, InferenceFailed, InferenceTimeout
25
26client = SegmindClient() # reads SEGMIND_API_KEY
27payload = {
28 "text": "Introducing the AI-enhanced Skyline T-800. [laugh] It's got integrated AI for superior performance. Want to explore pricing?",
29 "reference_audio": "https://segmind-resources.s3.amazonaws.com/output/70e9a9dd-e0f4-450f-a590-872996b44a01-chatterbox-turbo-input.mp3",
30 "temperature": 0.7,
31 "seed": 42,
32 "min_p": 0,
33 "top_p": 0.9,
34 "top_k": 500,
35 "repetition_penalty": 1.3,
36 "norm_loudness": True,
37}
38job = client.submit_async("chatterbox-turbo-tts", **payload)
39print(job.request_id) # available immediately
40try:
41 result = job.wait(timeout=600, interval=1.0)
42except InferenceTimeout as e:
43 print("still running:", e.request_id)
44except InferenceFailed as e:
45 print("failed:", e.detail)API Endpoint
https://api.segmind.com/v1/chatterbox-turbo-ttsParameters
reference_audiorequiredstring (uri)Provide a reference audio URL for voice matching. Use a public link for seamless access.
textrequiredstringEnter text to synthesize into speech. Use sound tags like [chuckle] for expression.
min_poptionalnumberSet minimum token probability. Higher values filter out unlikely outputs.
0Range: 0 - 1norm_loudnessoptionalbooleanNormalize audio to standard loudness. Recommended for consistent volume across outputs.
truerepetition_penaltyoptionalnumberPenalty for repeated words. Higher values reduce redundancy in speech.
1.3Range: 1 - 2seedoptionalintegerSet random seed for reproducible results. Zero for random, specific value for consistency.
42temperatureoptionalnumberAdjust creativity and expressiveness in speech. Use lower for consistency, higher for diversity.
0.7Range: 0.05 - 2top_koptionalintegerLimit to top K likely tokens. Lower for concise, higher for diverse expressions.
500Range: 0 - 1000top_poptionalnumberControl randomness via cumulative probability tokens. Lower for predictable, higher for varied outputs.
0.9Range: 0 - 1Response Type
Returns: Audio
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/chatterbox-turbo-ttsSubmit — 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