Build an AI Audiobook Narrator with Telnyx AI Inference, TTS, and Cloud Storage

Telnyx released a Flask app that uses AI Inference, text-to-speech, and cloud storage to automatically narrate audiobooks from raw text, outputting MP3 files with presigned URLs for playback. The pipeline splits text into chapters, adds narration cues, and renders audio via a single API flow, enabling self-publishing, accessibility, and content repurposing tools.

Turning a manuscript into a narrated audiobook traditionally means hiring a voice actor, booking studio time, and accepting that revisions cost hours of re-recording. This walkthrough builds a Flask app that takes raw text, uses AI Inference to chunk it into chapters with pacing and emotion cues, narrates each chapter with text-to-speech, and stores the resulting MP3s in Telnyx Cloud Storage with presigned URLs for playback. The canonical code example lives in the Telnyx code examples repo: https://github.com/team-telnyx/telnyx-code-examples/tree/main/ai-audiobook-narrator-python What This Example Builds A single-file Flask app with five endpoints: | Method | Path | Purpose | |---|---|---| POST | /books/narrate | Submit text for audiobook narration the main pipeline | GET | /books/<book id | Retrieve a specific book and its chapter audio URLs | GET | /books | List all books processed so far | GET | /voices | List available narrator voices | GET | /health | Service health check | The pipeline runs in three stages. AI Inference splits the submitted text into chapters and adds narration cues tone, pacing, emphasis . Text-to-speech renders each chapter as an MP3 using a consistent voice. Cloud Storage holds the final audio and returns a time-limited presigned GET URL for each chapter so callers can stream the result without handling long-lived credentials. Why This Matters The audiobook narrator exercises three Telnyx AI products in a single request flow — AI Inference, TTS, and Cloud Storage — and returns a tangible artifact an actual MP3 file instead of a text completion. That makes it a useful reference for anyone building content-generation pipelines where the output is media, not text. Developers use this pattern as the foundation for: Self-publishing tools — Convert manuscripts to audiobooks for distribution platforms that require audio Accessibility services — Turn written content into audio for visually impaired readers Content repurposing — Generate audio versions of blog posts, documentation, or newsletters Podcast pre-production — Draft narration tracks that a human host can later rerecord or remix Multi-language narration — Run the same text through different TTS voices and languages for localized audio Products Used telnyx products: AI Inference, TTS, Cloud Storage Telnyx AI Inference exposes an OpenAI-compatible API for chat completions. Telnyx TTS generates speech from text via POST /v2/ai/generate . Telnyx Cloud Storage is S3-compatible, so the AWS SDK boto3 talks to it directly — the Telnyx API key is used as both the access key and the secret key, and the endpoint host is region-scoped https://{region}.telnyxcloudstorage.com . Architecture POST /books/narrate | v +----------------------+ | AI Inference | chunks text into chapters, | /v2/ai/chat/ | adds tone + pacing cues | completions | +----------+-----------+ | v +----------------------+ | TTS Generate | renders each chapter as MP3 | /v2/ai/generate | with a consistent voice +----------+-----------+ | v +----------------------+ | Cloud Storage S3 | PutObject per chapter, | boto3 put object | presigned GET URL returned +----------+-----------+ | +--- JSON response with storage urls The Code The full app is 242 lines in a single app.py . The key pieces: Configuration and storage client. The Telnyx API key is loaded from the environment and used for both the REST API Inference, TTS and the S3 client Cloud Storage . The S3 client is pointed at the region-scoped Telnyx endpoint with s3v4 signing: python import os, boto3 from botocore.config import Config TELNYX API KEY = os.getenv "TELNYX API KEY" REGION = os.getenv "TELNYX STORAGE REGION", "us-central-1" s3 = boto3.client "s3", endpoint url=f"https://{REGION}.telnyxcloudstorage.com", aws access key id=TELNYX API KEY, aws secret access key=TELNYX API KEY, region name=REGION, config=Config signature version="s3v4" , AI Inference call. A system prompt instructs the model to break the text into chapters and return a JSON array with chapter number , chapter title , narration text , tone , and pacing fields. The response is parsed as JSON, with a fallback to paragraph splitting if the model returns malformed JSON: python def inference messages, max tokens=4000 : resp = requests.post f"{API}/ai/chat/completions", headers=HEADERS, json={ "model": AI MODEL, "messages": messages, "max tokens": max tokens, "temperature": 0.3 }, timeout=60 resp.raise for status return resp.json "choices" 0 "message" "content" TTS generation. Each chapter's narration text is sent to POST /v2/ai/generate with the chosen voice and output format: mp3 . The response body is the raw MP3 bytes: python def tts generate text, voice=None : resp = requests.post f"{API}/ai/generate", headers=HEADERS, json={ "model": TTS MODEL, "voice": voice or DEFAULT VOICE, "text": text, "output format": "mp3" }, timeout=60 resp.raise for status return resp.content Upload to Cloud Storage. Each chapter MP3 is uploaded with put object , then a presigned GET URL valid for one hour is returned so the caller can stream the audio without exposing long-lived credentials: python def upload to storage bucket, key, data, content type="audio/mpeg" : s3.put object Bucket=bucket, Key=key, Body=data, ContentType=content type return s3.generate presigned url "get object", Params={"Bucket": bucket, "Key": key}, ExpiresIn=3600 The narrate endpoint. Wires the three stages together, with graceful fallback if the AI chunking returns malformed JSON splits the text by paragraphs instead : python @app.route "/books/narrate", methods= "POST" def narrate book : data = request.get json or {} if not data: return jsonify {"error": "invalid request body"} , 400 title = data.get "title", "Untitled" text = data.get "text", "" voice = data.get "voice", DEFAULT VOICE if not text: return jsonify {"error": "Provide 'text' to narrate"} , 400 book id = f"book-{uuid.uuid4 .hex :8 }" Step 1: AI chunks text into chapters with narration cues try: chunking result = inference {"role": "system", "content": "You are an audiobook production assistant..."}, {"role": "user", "content": text :15000 } , max tokens=4000 chapters = json.loads chunking result except json.JSONDecodeError: Fallback: split by paragraphs paragraphs = p.strip for p in text.split "\n\n" if p.strip chapters = { "chapter number": i + 1, "chapter title": f"Chapter {i + 1}", "narration text": chunk, "tone": "warm", "pacing": "moderate" } for i, chunk in enumerate paragraphs Step 2 + 3: TTS per chapter → Cloud Storage for chapter in chapters: audio = tts generate chapter "narration text" , voice=voice key = f"{book id}/chapter-{chapter 'chapter number' :02d}.mp3" url = upload to storage BUCKET NAME, key, audio books book id "storage urls" .append url return jsonify { "book id": book id, "title": title, "status": "complete", "chapters": len books book id "chapters" , "storage urls": books book id "storage urls" } , 201 Run It git clone https://github.com/team-telnyx/telnyx-code-examples.git cd telnyx-code-examples/ai-audiobook-narrator-python cp .env.example .env add TELNYX API KEY, optionally tune AI MODEL, TTS MODEL, BUCKET NAME pip install -r requirements.txt python app.py The server starts on http://localhost:5000 . Create a bucket named audiobooks in the Telnyx Portal https://portal.telnyx.com/storage or set BUCKET NAME to an existing bucket and submit a chunk of text: curl -X POST http://localhost:5000/books/narrate \ -H "Content-Type: application/json" \ -d '{ "title": "The Future of Infrastructure", "text": "Chapter 1: The shift from cloud-edge to carrier-edge compute is changing where latency-sensitive workloads run...", "voice": "nova" }' The response includes a book id and a list of presigned storage urls , one per chapter: { "book id": "book-a1b2c3d4", "title": "The Future of Infrastructure", "status": "complete", "chapters": 3, "total audio mb": 2.1, "voice": "nova", "storage urls": "https://us-central-1.telnyxcloudstorage.com/audiobooks/book-a1b2c3d4/chapter-01.mp3?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Expires=3600&...", "https://us-central-1.telnyxcloudstorage.com/audiobooks/book-a1b2c3d4/chapter-02.mp3?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Expires=3600&...", "https://us-central-1.telnyxcloudstorage.com/audiobooks/book-a1b2c3d4/chapter-03.mp3?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Expires=3600&..." } Open any storage url in a browser or stream it from a client to hear the narrated chapter. Available Voices The app exposes five narrator voices out of the box: | Key | Voice | Character | |---|---|---| warm female | nova | Warm, expressive — default narrator | deep male | onyx | Deep, authoritative | neutral male | echo | Neutral, measured | bright female | shimmer | Bright, energetic | calm neutral | alloy | Calm, even-tempered | List them at any time: curl http://localhost:5000/voices Pass any voice identifier in the voice field of the /books/narrate request. Going to Production This example uses an in-memory dict for book metadata, which is fine for local testing but loses state on restart. For production: Persistent storage — Replace the in-memory books dict with PostgreSQL or Redis so book metadata survives restarts Authentication — Add API key validation on every endpoint; the example has none Bucket provisioning — Ensure the BUCKET NAME exists in your Telnyx Cloud Storage region before the first request, or add a create bucket call on startup Long-form input — The chunking step truncates input to 15,000 characters. For full manuscripts, split the source text on the client and submit each section as a separate narrate request Presigned URL lifetime — URLs expire after one hour. For longer-lived access, generate new presigned URLs on demand from the stored object keys, or set the bucket to public read for public-domain content Webhook signature verification — If you expose this app via a public URL, validate incoming request signatures not required for the local-only flow shown here Monitoring — Add structured logging and alert on failed inference , tts generate , or upload to storage calls so you catch upstream issues early